Identity verification apparatus and method

Description

BACKGROUND OF THE INVENTION
The need for security in systems utilized in various types of financial, governmental, retail, manufacturing and other establishments, in order to prevent use of the system, or entry into the system, by unauthorized parties is a current and pressing problem. One solution to the problem is to provide reliable means to verify that the party requesting use of, or entry into, the system is, in fact, the person he or she claims to be. For the purpose of verifying the identity of an individual, some unique personal characteristics such as, for example, facial features, fingerprints, voice patterns or signature of the individual may be employed.
One suitable characteristic is the force pattern of an individual's signature. Systems have been developed which are capable of distinguishing between a forged signature and a valid signature on this basis. This may be accomplished by detecting individually distinctive force characteristics of a signature to be tested and converting them into electrical signals which can be automatically processed and compared with the stored representation of an authentic signature, for determination of whether or not the tested signature is a valid one.
A number of United States Patents have issued which are directed to signature verification, including U.S. Pat. Nos. 3,480,911; 3,579,186; 3,618,019; 3,818,443; 3,859,515; 3,906,444; 3,959,769; 3,962,679; 3,983,535; 4,028,674; 4,035,769; 4,040,011; 4,040,012; and 4,086,567.
A continuing need exists for signature verification systems which provide increased accuracy, reliability and speed of operation. The system which is the subject of the present invention offers a novel arrangement which is readily and conveniently implemented to provide the signature vectors which enable comparisons to be carried out for the purpose of verification with a high degree of accuracy.
SUMMARY OF THE INVENTION
This invention relates to signature verification systems, and more particularly relates to such a system wherein an analog waveform derived from a signature is used in the generation of Haar coefficients included in a signature vector representative of such signature.
In accordance with one of the embodiments of the invention, apparatus for identifying the writer of handwritten information comprises a source of identifying indicia corresponding to the individual handwriting characteristics of said writer and comprising a reference vector and a threshold; means responsive during the writing of such information for generating a first signal representative thereof; means for deriving an information vector representative of said first signal; means for comparing said information vector with said reference vector and including means for generating a second signal indicative of said comparison; and means for comparing said second signal with said threshold and including means for providing an identifying signal whenever said second signal bears a predetermined relationship to said threshold.
In accordance with another embodiment of the invention, a method for verifying the identity of a person from samples of handwriting comprises the steps of deriving an information vector from a handwriting sample of a person whose identity is to be verified; providing identification indicia assigned to the person whose signature is to be verified; comparing said information vector with a reference vector associated with the identification indicia provided to derive an error value representing the variance between the two vectors; comparing said derived error value with a threshold value associated with the identification inidicia provided; and providing indication of acceptance if the derived error value is less than the threshold value and providing indication of rejection if the derived error value is greater than the threshold value.
It is accordingly an object of the present invention to provide an improved signature verification system.
Another object is to provide an improved method of signature verification.
An additional object is to provide an improved system and method for signature verification employing Haar coefficients.
A further object is to provide a method and apparatus for providing a compressed digitized representation of an analog signal.
A further object is to provide a method and apparatus for providing a compressed digitized representation of a signature.
A further object is to provide a method and apparatus for deriving a standard for verifying the identity of a person from samples of handwriting.
A further object is to provide a method and apparatus for deriving an information vector for verifying the identity of a person from a handwriting sample.
With these and other objects, which will become apparent from the following description, in view, the invention includes certain novel features of construction and combinations of parts, one form of embodiment of which is hereinafter described with reference to the drawings which accompany and form a part of this specification.

BRIEF DESCRIPTION OF THE DRAWINGS
FIG. 1 is a block diagram showing the hardware components of the signature verification system of the present invention.
FIGS. 2A, 2B and 2C together form a generalized flow diagram of the operation of the signature verification system of the present invention in the verification and reference modes.
FIGS. 3A, 3B, 3C and 3D show waveform representations of a signature at various stages of processing by the system.
FIGS. 4A and 4B together form a detailed flow diagram of the sequence of operations performed by the system in generating a compressed table of values for each signature.
FIG. 5 is a diagrammatic showing of various memory locations contained in the memory of the microcomputer system and the associated "secondary" storage units.
FIG. 6A is a diagrammatic showing of a digitized representation of a typical signature or segment thereof.
FIG. 6B is a table showing compressed values of data representing the waveform of FIG. 6A.
FIGS. 7A and 7B together form a detailed flow diagram showing the operation of the system in the reference mode.
FIG. 8 is a detailed flow diagram showing the operation of the system in computing time normalizing parameters, used in the reference mode.
FIG. 9 is a detailed flow diagram showing the operation of the system in computing time normalizing tables, used in the reference and verification modes.
FIGS. 10A, 10B, 10C and 10D together form a detailed flow diagram showing the operation of the system in computing the signature vector, used in both the reference and verification modes.
FIG. 11 is a diagrammatic representation of certain Haar functions.
FIG. 12 is a graphical representation of a signature waveform divided into a number of areas which are utilized in computing Haar coefficients.
FIG. 13 is a graphical representation of the varying value of a given Haar function over a specified range.
FIG. 14 is a detailed flow diagram showing the operation of the system in generating reference values used in the reference mode.
FIGS. 15A and 15B taken together form a detailed flow diagram showing the operation of the system in generating certain special values used in the reference mode.
FIG. 16 is a detailed flow diagram showing the operation of the system in analyzing signature vectors, said operation being used in the reference mode.
FIGS. 17A and 17B together form a detailed flow diagram showing the operation of the system in the verification mode.
FIG. 18 is a detailed flow diagram showing the operation of the system in saving the signature samples in memory.

DESCRIPTION OF THE PREFERRED EMBODIMENT
Referring now to the drawing, a signature verification system is shown in block form in FIG. 1. This system comprises a central processor unit 100, which includes a suitable microcomputer system, such as, for example, an Intel 80/10 microcomputer system. The unit 100 controls, by means of a software operating system, the input-output peripheral units which are connected to a common data bus 102 and also contains all algorithms and performs all computations required for the personal verification system.
The unit 100 includes a memory 80, a partial map of which is shown in FIG. 5. Included in said memory are a location 82 for storage of programs during operation, a location 84 for storage of data representing signatures or other handwritten data made for reference or verification purposes by customers, a location 86 for storing data representing five different signature samples, a common storage location 88 in which the data for the individual signature tables is collected, a location 90 used in performing normalizing operations, a location 92 for receiving reference signature data to be used in verification operations from a storage location 94 in "secondary" storage unit 116, and initially calculating such data for storing in location 94 of storage unit 116, a location 96 in which signature vectors for five signatures are stored, and a common storage location 98 which is used in generation of the individual signature vectors. As used herein, the term "signature vector" refers to a digital representation of certain defined characteristics of a handwriting sample, which may be a signature, but is not limited to such. The term "information vector" could be used in place of "signature vector", if desired.
A plurality of customer interface units are provided to enable the customer to perform the required actions for verification of identity, and to guide the customer in performing the necessary actions in the proper sequence.
A first such unit connected to the data bus 102 is the lead-through unit 104, which provides instructions to the customers as to the sequence of operations to be followed. The various indicators and their significance are tabulated below:
______________________________________ID # Enter identity claim numberSIGN Sign on signature padACCEPT Positive verificationREJECT Negative verificationREF System is in reference modeVERIFY System is in verify mode______________________________________
A second unit connected to the data bus 102 which may be employed is a speaker 106 which provides an audible tone each time that a signature is required by the system.
An additional unit connected to the data bus 102 is the signature pad unit 108 on which the customer executes the signature to be verified. A window 110, located above a force-sensitive surface, over which a record medium for receiving the signature travels, defines the signing area, and an associated paper feed mechanism 112, also connected to the data bus 102, advances the record medium after the signature has been completed. Any suitable signature pad structure may be employed, with one such suitable unit being disclosed in the U.S. Pat. No. 4,143,357, issued Mar. 6, 1979, inventors Donald W. Baver et al., and assigned to the assignee of the present application. Any suitable means may be employed for compensation for drift of the signature table or pad from a null position, one such method and apparatus being disclosed in the co-pending application Ser. No. 016,677, filed Mar. 1, 1979, inventor Robert M. Whitely, and assigned to the assignee of the present application.
Another unit connected to the data bus 102 is a key pad 114, by means of which information, such as a customer identification number, can be entered into the system. In the illustrated embodiment, the key pad unit contains twelve keys, including ten digits, one "clear" and one "enter" key.
In addition to the customer interface units described above, two other units are connected to the data bus 102 in the illustrated embodiment.
One of these is a storage unit 116, which in the illustrated embodiment takes the form of a dual drive diskette which is used to store information required by the system, such as standards generated from the signatures of those customers who have been made a part of the system, programs for the system, and associated information utilized in performing the operations for which the system is designed.
Another unit is a printer/keyboard unit 118, which may be used to input commands to load programs from the storage unit 116, and to provide means for outputting the results of transactions performed on the system, as for example during testing operations.
The operating system software provides two operating modes: reference and verification.
The reference mode is utilized for enrollment of a person into the system so that his identity can be verified by the system at subsequent times whenever desired. In the reference mode, an ID claim number is assigned for each customer, a number (five in the illustrated embodiment) of signatures are requested by the system and are made by the customer, a "standard" or "reference" is generated by the system from the five signatures, and the standard is stored in the storage unit 116 for later accessing by the ID number in subsequent verification of customer identity.
In the verification mode of operation, a customer enters his or her ID number into the system via the key pad unit 114, the standard for such ID number is fetched from location 94, a signature is requested by the system through the lead-through unit 104, the signature is made by the customer on the signature pad unit 108, the signature is compared to the standard, and the result is displayed on the unit 104. It will be recognized that the customer ID number could be entered into the system by other means than manual keying, such as, for example, a transaction card on which the ID number is stored magnetically, optically or by other means. Multiple tries, up to a predetermined number, may be permitted by the system if desired.
FIGS. 2A, 2B and 2C provide a generalized flow diagram of system operation, and also include, by means of the block representations at the right of these figures connected to flow diagrams by horizontal lines, a reference to the system peripheral units which are involved in the various steps of the operations. It may be noted that appropriate software for driving these peripheral units is provided, and interacts with the system programs which control the overall operations, and which are loaded from the storage unit 116 (FIG. 1) into the microcomputer system 100.
With the system on and in condition to commence operation, it is in the "verify" mode, as represented by block 126 (FIG. 2A); the lead-through unit 104 shows the verify indicator "V" on and the "ID#" indicator on, as represented by line 124; and the system is ready to accept an identity claim number (ID#) from the key pad unit 114, as indicated by line 122. If a special code (illustratively 999) is entered as an ID#, in place of the normal customer ID# which would be used in the verification mode, the system will switch through a decision block 128 to the reference mode, represented by block 130, for generating a standard. One standard is maintained for each customer using the system. It is generated in the reference mode, is updated after each successful verification attempt, and is stored in the storage unit 116, being indexed by ID#.
Referring now to the generalized flow diagram of FIG. 2C, it may be seen that with the system in the reference mode, as indicated by block 130, the lead-through unit 104 shows the verify indicator V off, and the reference and ID# indicators on. The customer then enters his or her assigned ID#, which causes the ID# indicator to go off, the sign indicator to go on, and an audible tone to sound from the speaker unit 106. The customer then signs a signature on the pad 108, which causes the sign indicator to go off and the record medium to be advanced. A signature vector is computed, using the force relationships generated by the signature, in a manner to be subsequently described, as designated by the signature vector block 132. This process is repeated until five sample signatures have been written, a signature vector is computed for each, and each vector is tested for validity with respect to the vectors taken as a whole to detect abnormal signatures, as represented by the decision blocks 134 and 136. Any invalid signatures are replaced, as indicated by the block 138.
Utilizing the signature vectors of the five valid signatures, a reference is then computed, as represented by block 140, and the reference is then stored in the storage unit 116. The system then returns to the verify mode, as represented by block 126.
A significant aspect of the system described herein is the generation of signature vectors from the signing of signatures by the customer on the signature pad 108, such signature vectors being used in both the reference and verification modes. The action of the writing instrument on the writing surface produces a force versus time relationship which is translated by the unit 108 into a voltage versus time relationship. A graphical representation of a typical signature is shown in FIG. 3A, with time represented by the horizontal coordinate and voltage by the vertical coordinate. The waveform 150 of FIG. 3A is then digitized by sampling it at a predetermined rate, which may typically be one hundred samples per second, as represented by the vertical lines 152 in FIG. 3B. Thus if making a signature takes seven seconds, there will be a total of seven hundred samples. The amplitudes of the samples thus derived are stored in memory.
The flow diagram of FIG. 18 sets forth the sequence of operations performed by the system in storing the magnitudes of the digitized samples represented by FIG. 3B in memory location 84 of memory 80, FIG. 5. In commencing this operation, the microcomputer system 100 of FIG. 1, after turning the SIGN indicator of unit 104 on, and sending an audible tone on unit 10, is ready to receive the digitized values from signature pad unit 108. In order to detect the start of a signature the magnitudes of the signature samples received are compared to an arbitrarily determined threshold value STHR. The first sample with magnitude larger than STHR marks the start of the signature. It will also be noted that the digitized values in the illustrated implementation of this invention may range from zero to a maximum 255. To detect the end of a signature, the number of consecutive zero magnitude samples encountered in the waveform is compared to a numerical value equal to a number of sample times sufficient in duration to exceed the vast majority of inter-signature pauses, or "pen lifts", by the writer, so that when this value is exceeded, a clear indication is provided that the signature has actually terminated. In the illustrated embodiment, the number 192 has been found to be a suitable value. This value is represented in FIG. 18 by LIM, which provides a means for distinguishing between "pen lift" situations and the end of a signature. It may be noted that the operation following commencement as indicated by the START block 900 (FIG. 18), proceeds under the conditions set forth in block 902. STHR may suitably be set equal to 10 in the illustrated embodiment; LIM may suitably be set equal to 192 in the illustrated embodiment, as previously described; ZCNT, representing the number of successive zero magnitude samples, is set equal to zero; i, representing the time, in number of samples, since the start of the signature, is set equal to one. Operation proceeds to block 904, where the system accepts one digitized value representing the magnitude of the waveform for sample number i, denoted by S.sub.i. The operation then proceeds to decision block 906 where the value S.sub.i is compared to STHR. Assuming S.sub.i is less than or equal to STHR, the operation loops back to block 904, where the system waits for the next sample to be generated by writing of a signature on signature pad unit 108 (FIG. 1). The same operational sequence is repeated until, in decision block 906, the magnitude of the sample S.sub.i is larger than the value STHR. The sample S.sub.i is then stored in memory location 86 as represented by block 910. It may be noted that the value i was maintained equal to one throughout this operation. The value i is now incremented by one, and the operation proceeds to block 912, where the system waits and accepts the next sample S.sub.i. Assuming that the magnitude S.sub.i is not equal to zero, the operation will loop through decision block 914, to block 916, where ZCNT is set to zero, and then back to block 910, where S.sub.i is stored in memory location 86. For the case that S.sub.i =0, operation will continue to block 918 where the zero counter is incremented by 1. Assuming that the current count i does not equal the predetermined limit of 192, as determined in decision block 920, the processing loop proceeds to blocks 910 and 912 to store the current sample S.sub.i and to receive the next sample. Let it be assumed that S.sub.i represents the end of the signature, so that sample amplitude thereafter equals zero for the required 192 samples. The operation will then loop through blocks 912, 914, 918, 920, 910 back to 912 until the zero counter reaches the value LIM equal to 192. At this time the operation continues to block 922 where the value T, representing the total signature time in number of samples, is computed by subtracting the value LIM from the current value i and adding one. The operation of storing the signature samples in memory location 84 is completed as shown by block 924. In the illustrated embodiment, each signature sample is represented by an 8-bit word.
The stored signature data is then processed to achieve a data compression of the digitized samples. If desired, this processing could be done in real time, rather than from storage, as is done in the illustrated embodiment. The process waveform 154 is shown in FIG. 3C. The waveform 156 of FIG. 3D is essentially the same as the waveform of FIG. 3C and shows certain of the time intervals and relationships relevant in processing the signature vector.
The flow diagram of FIGS. 4A and 4B sets forth the sequence of operations performed by the system of the present invention in generating a compressed table of values for each signature from which a signature vector can be computed in accordance with another sequence of operations, to be subsequently described. The flow diagram of FIGS. 4A and 4B will be described in association with reference to FIG. 6, which is an illustrative waveform representing a portion of a signature, not corresponding to the waveform of FIGS. 3A to 3D inclusive. A total of twenty-one sampling points are represented in FIG. 6, with the sample number corresponding to one of the twenty-one equal time divisions, and the corresponding point on the waveform representing a voltage amplitude. Certain of the sample numbers are identified by the designation S1, S2, etc.
Processing and compression of the signature data involves the determination of maximum and minimum points in the signature waveform and measurements of certain time characteristics of the signature. In order to be selected as a maximum or a minimum point, a sample value must not only reflect a change of sign in the slope of the waveform, as defined later, but must also differ in value from the preceding sample by more than a given threshold amount.
Referring to FIGS. 4A and 4B, it may be noted that S.sub.i represents the digitized value of the "ith" sample of the waveform. The value "i" represents the time, in number of samples, since the start of a signature. "MXMIN" represents the last maximum or minimum sample value maintained in storage. The values assigned to CODE are employed to describe certain waveform conditions during the operation. A value of one assigned to CODE means that the slope of the waveform is positive (S.sub.i+1 >S.sub.i); a value of two assigned to CODE means that the sample value S.sub.i is 0; and a value of three assigned to CODE means that the slope of the waveform is negative (S.sub.i+1 <S.sub.i).
In commencing the data compression operation from the START block 160 of FIG. 4A, a number representing the magnitude of the first sample S.sub.i is stored in TABLE 1 of the memory location 88 (FIG. 5), represented by block 168 of FIG. 4A, while the corresponding time (namely one) is stored in TABLE 2 of said memory location. It may be noted that the operation is commenced under the conditions set forth in block 162, namely CODE value set equal to 1; MXMIN value set equal to zero; a value of four assigned for the threshold THR; i, representing the sample number, is set equal to zero; and a SUM value, in which a cumulative total of sample magnitudes is maintained for the purpose of generating one of the values to be used in determining a signature vector, is set equal to zero. The value I, representing the entry number in TABLE 1 and TABLE 2, is set to one.
As shown in block 164, the system increments the value of i by one for each sample, fetches the corresponding sample value from memory location 84, and accumulates a running sum of sample magnitudes, which can be used in calculating a signature vector. Since i=1 at the beginning of the operation, the sample amplitude value S.sub.1 is stored as the first entry (I equals 1) in TABLE 1, and the i value of 1, representing sample time, is stored as the first entry in TABLE 2 of memory location 88. The value I is then incremented by one, as shown in block 168. The value I is now equal to two, as shown in block 168.
The first sample, for which i=1, which is fetched out of memory location 84, corresponds to point S1 on the waveform of FIG. 6A. System operation proceeds through decision blocks 170, 172 and over path 174 and said first sample is stored, as shown in block 176 (FIG. 4B) in an appropriate memory location (not shown) in memory 80 by virtue of the fact that the system is in CODE 1 condition and that the sample value exceeds MXMIN, which was initially set to zero.
The system then operates through a loop which includes path 178. The next sample, corresponding to point S2 on the waveform of FIG. 6A, is then routed through decision blocks 166, 170 and 172 of FIG. 4A, it being noted that S2 is greater in amplitude than the previous MXMIN of sample S1, and over path 174, and is stored in memory 80 in place of the previous stored S1 sample as the new MXMIN, as shown in block 176. Processing of samples continues with sample S3, which is greater in amplitude than previous sample S2, and which is stored in its place as the new MXMIN.
The fourth sample S4, which is less in magnitude than sample S3, as shown in FIG. 6A, is next processed. As a consequence of its comparison with MXMIN in block 172, it is then tested, as shown in block 180, to determine whether it is lesser in amplitude than MXMIN by a factor exceeding the previously established threshold of four. Since it is not, system operation loops back over path 182 to path 174, and sample S4 is then stored as the new MXMIN, in place of the previously stored S3. The system then loops back over path 178 to receive the next sample, as previously described.
The same sequence of operation as described above continues as samples S5 to S9 inclusive are processed by the system. In each case, the new sample replaces the previous sample as MXMIN, as represented in block 176.
When sample S10 is processed, it is substantially lower in amplitude than MXMIN as determined in block 172, and is therefore tested in block 180. Since MXMIN exceeds S10 by more than the threshold of four, processing continues as shown in block 184, in which the CODE is changed from 1 to 3, and the previous MXMIN (corresponding to S9) is stored in TABLE 1 of the selected memory location 88, as the second entry (I is two) in that table, while i minus 1 (which equals 9) is stored in TABLE 2, also as the second entry. The value of I is then incremented by one, assuming a value of three. System operation then loops back over path 186 to path 174, and sample S10 is stored as the new MXMIN, in place of the previously stored S9. The system then loops back over path 178 to receive the next sample.
When sample S11 is processed, the CODE is now 3, and processing therefore proceeds over path 188 to decision block 190 (FIG. 4B) for a determination of whether or not the magnitude of sample S11 equals zero. Since it does not, processing continues to decision block 192, where the sample S11 is compared to the MXMIN, and found to be lesser in magnitude, so that processing continues along path 194 and sample S11 is stored in place of the current MXMIN, as shown in block 176.
Sample S12 is then processed through blocks 170 and 190, and since its magnitude is equal to zero, processing continues as shown in block 196. The CODE is changed from 3 to 2, zero is stored as the third entry (I equals three) in TABLE 1 of memory location 88, representing the magnitude of sample S12, and 12 is stored as the third entry in TABLE 2 representing the sample time. The value I is incremented by 1, to four. Operation continues to block 202, where the current value of i is compared to the total number of samples T. As it is not equal to the total number of samples T, operation of the system then loops back over path 178 to receive the next sample.
Since CODE is equal to two, and sample S13 is also zero in magnitude, processing proceeds from block 170 over path 198, to block 200, and the processing loop returns to block 164 to receive the next sample.
Since sample S14 has a positive amplitude, system processing continues from block 200 to block 204, where the code is changed from 2 to 1, zero is stored as the fourth entry in TABLE 1, and thirteen (14-1) is stored as the fourth entry in TABLE 2, representing the sample time; I is incremented by one, so that I equals five. Processing proceeds over path 174 and the amplitude of sample S14 is stored as MXMIN, as shown in block 176, after which the system loops over path 178 to receive the next sample.
It may be noted that the interval between the two zeroes stored in TABLE 1, as measured by the sample times stored in TABLE 2, represents a "pen lift" during the signature process, such as may take place between the signing of first and last names, or between a name and an initial.
Processing of samples S15 and S16 is accomplished in the manner previously described, resulting in the storage of the amplitude S.sub.i and time i of sample S15, in TABLE 1 and TABLE 2 respectively for I=5. Similarly, the processing of samples S17 and S18 is carried on. When sample S19 is processed, the system follows the CODE 3 path 188 from block 170 through decision blocks 190, 192 and 206 to perform the functions set forth in block 208. The CODE is changed from 3 to 1; the MXMIN value, corresponding to the amplitude of sample S18, is stored in TABLE 1, and the sample time value of 18 is stored in TABLE 2. Thereafter the amplitude of sample S19 is stored as MXMIN.
Samples S20 and S21 are then processed in the manner described above. Let it be assumed that sample S21 represents the end of the signature, so that sample amplitude thereafter equals zero for the required one hundred ninety-two samples. It will be seen that sample S21 will cause the CODE to be changed from 3 to 2; zero is stored as the Ith entry in TABLE 1 of memory location 88, representing the magnitude of sample S21, and 21 is stored as the Ith entry in TABLE 2, representing the sample time. The value I is incremented by one. Operation proceeds to decision block 202. This time the value i is equal to the total number of samples T, at which the system functions as shown in block 210, to save the current amounts stored in TABLE 1 and TABLE 2, the number of entries NKX, and the sum of the sample magnitudes SUM, by shifting them from memory location 88 to the appropriate location in the memory area 86, and to stop, as shown in block 212.
TABLE 1 and TABLE 2 are thus loaded in location 88 to store the compressed significant information concerning the signature just made, and these tables, when shifted to location 86, can then be employed to derive a signature vector which can be used in either the reference or the verification mode of operation of the system.
FIG. 6B shows TABLE 1 and TABLE 2 entries corresponding to the waveform of FIG. 6A for the various entries I.sub.1 to I.sub.8. For this waveform, NKX equals eight, and SUM equals 253, which represents the sum of all of the values of S.sub.i from i equals 1 to i equals 21.
A detailed description of the operation of the system in the reference mode will now be provided, in connection with the flow diagram appearing in FIGS. 7A and 7B, as well as certain additional flow diagrams which set forth in greater detail specific parts of FIGS. 7A and 7B.
As shown in FIG. 7A, system operation in the reference mode is commenced by entering an ID# "k" into the keyboard unit 114. This number is saved in an appropriate location in storage, as indicated in block 220. A quantity "J", representing the number in a suitable memory location of a group of signatures to be made by a customer to establish a standard, is set equal to zero in block 222. A quantity "W", representing the number of times that a customer "k" is permitted to replace invalid signatures, is set equal to zero in block 223. The quantity "J" is incremented by one in block 224.
The customer is then directed in block 226 to make a signature on unit 108, which converts said signature to digital voltage samples in block 228. TABLE 1 and TABLE 2 are computed from said samples in block 230, utilizing the process shown in FIGS. 4A, 4B, as previously described, and stored in memory location 86 (FIG. 5), as represented in block 232. Decision block 234 causes this process to be repeated until tables for five signatures have been computed and stored, at which time the process continues over path 236 to block 238, where time normalizing parameters are computed. The time normalization process is required to compensate for the differences in the duration of the pen lift regions of different signatures of the same person.
The detailed flow diagram for block 238 of FIG. 7B is shown in FIG. 8. The time normalizing process is commenced in block 242 by the setting to zero of the signature number "J" in an appropriate memory location.
As represented by block 244, a number of quantities stored in suitable memory locations are set to zero, including the following, which have meanings as described below:
SMRPL--is the sum of the pen lifts in all of the signatures to be considered (five in the illustrated embodiment).
SMRPLS--is the sum of the samples in the pen lifts in all of the signatures to be considered.
SMRT--is the sum of the time durations of all of the signatures to be considered.
In block 246, the signature number (J) is incremented by one, and in block 248, the quantities PL(J) and PLS(J) are set equal to zero. PL(J) represents the number of pen lifts in a signature (J), during which force and therefore voltage amplitude are zero, and PLS(J) represents the number of samples taken during the pen lifts in a signature (J). In addition, in block 248, the quantity NKX in an appropriate memory location is set equal to the total of the number of entries in TABLE 1, which equals the number of entries in TABLE 2, for the signature (J).
In block 250, a quantity T(J) in a suitable memory location is set to be equal to the total time duration, measured in number of samples, of the signature (J), which corresponds to the last entry of Table 2 for that signature. In block 252, a quantity corresponding to the entry number I for TABLE 2, in a suitable memory location, is set equal to zero, and in block 254, the entry number I is incremented by one.
The incremented entry number is then compared in decision block 256 to determine whether or not it is equal to the total number of entries in TABLE 1 or TABLE 2 for the signature being examined. If so, the system continues with the operation as represented by block 258, in a manner to be subsequently described. If not, the value of the Ith entry in TABLE 1 is checked against zero in decision block 260. This is for the purpose of determining a zero entry, indicating commencement of a pen lift, for this signature. If the entry is not zero, the operation loops back to block 254 to test the next entry. However if the entry value is zero, the entry number of incremented by one, as indicated in block 262, which will give the table entry corresponding to the end of the pen lift. After this, partial totals for number of pen lifts and number of pen lift samples for the signature J are computed as shown in block 264, by adding sums for the signature being tested to the corresponding existing partial sums for these quantities. The operation then loops back to block 254 to test the next entry.
This testing of entries in TABLE 1 continues until the comparison shown in block 256 indicates that I is equal to NKX, the last entry of TABLE 2. The system then branches to block 258, in which T(J), the last entry of TABLE 2, PL(J), the total number of pen lifts, and PLS(J), the pen lift sample total, all for signature J, are stored in an appropriate memory location in memory 80. Following this, the cumulative quantities SMRPL, SMRPLS and SMRT for the signatures processed thus far are calculated, as shown in block 266.
The system then determines whether all five signatures have been tested, as shown in decision block 268. If not, the operation of the system loops back to block 246 for processing on the next signature. If J=5, indicating that all five signatures have been processed, the quantities RPL, RPLS and RT are next determined, as shown in block 270, by dividing the quantities SMRPL, SMRPLS, and SMRT, respectively, by five. The quantities PL, PLS, T, RPL, RPLS and RT are identified as follows:
PL--is the number of pen lifts in the signature bein considered.
PLS--is the number of samples in pen lifts in the signature being considered.
T--is the total signature time, in number of samples.
RPL--is the average number of pen lifts per signature in the signatures being processed.
RPLS--is the average number of samples in pen lifts per signature in the signatures being processed.
RT--is the average time duration per signature in the signatures being processed.
From block 270, the description of system operation returns to FIG. 7B, over path 240. As shown in block 272 of FIG. 7B, J is set equal to zero, and then is incremented by one, as shown in block 274. Following this, time normalizing tables are computed as shown in block 278, following path 276. The computation of time normalizing tables represented generally in block 278 is shown in greater detail in FIG. 9.
The necessity for use of time normalization of pen lift regions of a signature when that signature is to be compared with another signature of the same person arises from the observation that the number of pen lifts and the time durations of pen lifts for a person change significantly from signature to signature. In order to provide that consistency necessary for reliable comparisons in force waveforms of different signatures of the same person, it is necessary to align the pen lift regions of the signatures.
An algorithm which may be employed for time alignment of pen lift regions is derived in the manner described below, employing the quantities RPL, RPLS, RT, PL, PLS, T and PLFCTR. PL, PLS, T, RPL, RPLS and RT have been previously defined. PLFCTR is a factor derived by a subsequent equation by which the number of pen lift samples in a signature is multiplied in a normalizing operation.
For purposes of this discussion, "current signature" will be considered to be a signature having the quantities PL, PLS and T; and "reference signature" a signature having the quantities RPL, RPLS and RT. This algorithm will align the pen lift regions of the current signature to the corresponding pen lift regions of the reference signature.
The change in the number of pen lift samples due to difference of number of pen lifts between the reference and current signatures is:
.DELTA.PLS=RPLS/RPL(.+-.RPL.-+.PL) (1)
An adjusted value PLS' of the number of pen lift samples for the current signature is derived in accordance with the following expression, which incorporates a quantity equal to one half of .DELTA.PLS:
PLS'=(RPLS.-+.(1/2).DELTA.PLS).multidot.(T'/RT) (2)
Replacing (1) into (2), ##EQU1## It should be noted that by adjusting the pen lift regions of the current signature, the total time of the current signature does not remain T, as indicated in equations (2) and (3) by T'.
To determine the value of T' it should be noted that the "pen down" or writing time between the current signature and the adjusted one remains constant:
writing time=T-PLS=T'-PLS' (4) ##EQU2## then,
T-PLS=T'-X.multidot.T'
T'=(T-PLS/1-X) (6)
PLS'=(X/1-X)(T-PLS) (7)
The actual number of samples in the pen lift regions of the current signature is PLS: therefore the adjusted number of samples in each pen lift of the current signature will be found by multiplying the actual number of pen lift samples in each pen lift by the following factor:
PLFCTR=(X/1-X)(T/PLS-1) (8)
where x is given in equation (5).
Referring once again to FIG. 9, the pen lift multiplying factor is computed from equation (8), as shown in block 282. Tables TABLE 1 and TABLE 2 for signature J are transferred from memory location 86 of memory 80 (FIG. 5) to memory location 88. Following this, as shown in block 284, the quantity NKX, in a suitable location in the memory 80, is set equal to the number of entries in TABLE 1. The quantity "CHANGE", in a suitable location in memory 80, representing the difference between the normalized number of samples and the original number of samples in TABLE 2 for a given signature, is set equal to zero. In addition, the entry number I for TABLE 1 and TABLE 2, stored in a suitable location in memory 80, is set equal to zero.
The system then continues operation by incrementing the quantity I by one, as shown in block 286, and proceeds to decision block 288 for a determination of whether or not I is equal to the total entries of TABLE 1 (or TABLE 2, since they are the same) plus one. If so, the operation of the system proceeds over path 280 back to the sequence shown in FIG. 7B. If not, the system proceeds to the operations shown in block 290, in which the quantity stored in location 88 of memory 80 (FIG. 5) for the I entry of TABLE 1 is stored in location 90 of memory 80 as NORMALIZED TABLE 1, and in which the quantity stored in location 88 for the I entry of TABLE 2 is modified by the CHANGE quantity and is stored in location 90 as NORMALIZED TABLE 2.
Next, as shown in decision block 292, a determination is made as to whether or not the original I entry of TABLE 1 is equal to zero. If not, operation of the system loops over path 294 back to block 286. If so, operation of the system proceeds with the computations shown in block 296. Entry I is set equal to I+1. The I entry of NORMALIZED TABLE 1 is set equal to zero. The pen lift period is calculated by subtracting the I-1 entry of TABLE 2 from the I entry of TABLE 2 and adding one. The normalized pen lift period is calculated by multiplying the original pen lift period by the factor PLFCTR, previously computed in block 282.
Operation of the system then proceeds as shown in block 298 with calculation of the I entry of NORMALIZED TABLE 2 by adding the integer closest to the previously calculated normalized pen lift period to the I-1 entry of NORMALIZED TABLE 2 and subtracting one. CHANGE is then computed by subtracting the I entry of TABLE 2 from the I entry of NORMALIZED TABLE 2.
System operation then loops back over paths 300 and 294 to block 286 and continues, with the calculated CHANGE quantity being used in block 290. As previously described, system operation continues until the incremented I entry value in block 286, equals the total number of entries in TABLE 1, plus 1, at which time the system operation continues over path 280 to block 302 of FIG. 7B, in which the information stored in location 90 of memory 80 (FIG. 5) is utilized in computing the signature vector for signature J. The computation of the signature vector is shown in greater detail in FIGS. 10A, 10B, 10C and 10D.
As shown in block 304 of FIG. 10A, system operation proceeds by dividing the total time required for a signature J into sixteen equal intervals, providing sixteen distinct regions or divisions of the force pattern. This is accomplished by dividing the total number of signature samples by sixteen. Next, as shown in block 306, the sixteen areas of the sixteen regions under the signature force waveform are computed and labelled A1 through A16.
These sixteen areas are used in computing Haar coefficients. The Haar system of functions was originally formulated by A. Haar, and is described in "Zur Theorie der Orthogonalen Funktionensysteme", Math. Annalen., Vol. 69, pp. 331-371, 1910, by A. Haar. It is a set of complete orthogonal functions defined over the interval [0, 1]. In the non-normalized form, Haar functions are described by 1's, -1's and 0, and therefore can be conveniently represented in a digital computer.
An important feature of the Haar transformation is that it samples the input waveform at progressively coarser intervals starting with the highest resolution and decreasing in powers of two. This feature makes the Haar transformation both locally sensitive and globally sensitive.
The Haar function system has been used for several applications since 1968. Andrews and others use it for optical data processing and signal processing by considering the Haar transformation as another class of Fourier transforms. See Andrews, H. C., Computer Techniques in Image Processing, Academic Press, 1970; Andrews, H. C. and Kane, Jr., "Kronecker Matrices, Computer Implementation, and Generalized Spectra", JACM, Vol. 17, pp. 260-268, April 1970. Andrews, H. C. and Caspari, K. L., "A Generalized Technique for Spectral Analysis", IEEE Trans. on Computers, Vol. C-19, No. 1, pp. 16-25, January 1970. Bremmerman and Meltzer use Haar transformation for speech recognition and speech synthesis. See Bremmerman, H. J., "Pattern Recognition, Functionals, and Entropy", IEEE Trans. on Bio-Med. Eng., Vol. BME-15, pp. 201-207, 1968; Meltzer, D., "Speech Synthesis by Haar Functions with Comparison to a Terminal Analog Device", Ph.D. Dissertation, Ohio State University, 1972; and Meltzer, D., Lehiste, I., "Vowel and Speaker Identification in Natural and Synthetic Speech", JASA, Vol. 51, p. 131 (A), Janurary 1972. The Haar transformations have also been used in recognition of patterns by feature selection through orthogonal expansions. See Andrews, H. C., "Multidimensional Rotations in Feature Selection", IEEE Trans. on Computers, Vol. C-20, No. 9, pp. 1045-1051, September 1971.
Fifteen components of a signature vector are determined by computing Haar coefficients, as shown in block 308. The Haar coefficients of order n for a function f(t), which function represents the force waveform of a signature, are defined as ##EQU3## where m is dependent on n, and for each value of n, m will have a total number of values equal to 2.sup.n, such values being all of the integers in the interval 1 to 2.sup.n, there being a number of Haar functions equal to the total number of values of m; and where .phi..sub.o (t) and .phi..sub.n.sup.m (t) are Haar functions which form a set of complete orthogonal functions defined over the interval [0, 1]. The Haar functions are defined as follows: ##EQU4## where .alpha.=2.sup.-n-1 ; n=0, 1, 2 . . . , and m=1, 2-2.sup.n.
The four Haar functions for .phi..sub.o and .phi..sub.n.sup.m for n equals zero and n equals one, and the variation of these functions over the time interval (0, 1), which may correspond to the total time interval of the signature force pattern, are shown in FIG. 11.
The function, f(t), for the force pattern may be represented by Haar series as ##EQU5##
As mentioned above, the total time T of the waveform represented by function f(t) is normalized to unity since the Haar functions are defined in the interval [0, 1]. For the computation of Haar coefficients from Eq. (10), the nonnormalized form of the Haar functions of Eq. (12) is described as follows:
.phi..sub.o (t)=1 (14) ##EQU6## where .alpha.=2.sup.-n-1, n=0,1,2, . . . , and m=1,2, . . . , 2.sup.n.
The Haar coefficients of f(t) computed from Eq. (10) are divided by C.sub.o, which represents the average amplitude of f(t), i.e., the average force applied during the writing of the signature, and stored in a suitable memory location of the memory 80, as shown in block 310. These new coefficients are designated P.sub.r, and constitute the first fifteen components P.sub.1 to P.sub.15 of the signature vector:
P.sub.r =C.sub.n.sup.m /C.sub.o for n=1, 2, 3. (16)
As an example, the computation of Haar coefficient C.sub.2.sup.3 (n=2, m=3) is presented below. C.sub.2.sup.3 is found from Eq. (10) using .phi..sub.2.sup.3 (t) from Eq. (15)
.alpha.=2.sup.-n-1 =1/8
and ##EQU7## .phi..sub.2.sup.3 (t) is graphically represented in FIG. 13. From Eqs. (10) and (16) ##EQU8##
In Eq. (17), 5/8.intg.1/2f(t)dt represents the area A.sub.9 +A.sub.10 shown in the time normalized waveform f(t) of FIG. 12 under the portion from t=1/2 to t=5/8; and 3/4.intg.5/8 f(t)dt represents the area A.sub.11 +A.sub.12 shown in FIG. 12 under the portion from t=5/8 to t=3/4. The difference of these two areas is Haar coefficient C.sub.2.sup.3, as shown in Eq. (18), which is normalized in accordance with Eq. (16) to provide the desired parameter P.sub.r.
For the purpose of signature verification, it has been observed that the first fifteen parameters P.sub.n.sup.m computed for n=0 (m=1), n=1 (m=1,2), n=2 (m=1,2,3,4), and n=3 (m=1,2, . . . , 8), are quite satisfactory. These fifteen parameters are labeled as p.sub.1, p.sub.2,-,p.sub.15. In these parameter equations, n and m have the same significance as described above in connection with the Haar coefficients C.sub.n.sup.m.
The fifteen values of C.sub.n.sup.m are computed in the following manner: Time T=1 is divided in sixteen equal time regions as shown in FIG. 12, and sixteen areas A.sub.1, A.sub.2, . . . , A.sub.16, under the waveform f(t) in the sixteen regions, are computed. Then
C.sub.3.sup.1 =A.sub.1 -A.sub.2
C.sub.3.sup.2 =A.sub.3 -A.sub.4
C.sub.3.sup.3 =A.sub.5 -A.sub.6
C.sub.3.sup.4 =A.sub.7 -A.sub.8
C.sub.3.sup.5 =A.sub.9 -A.sub.10
C.sub.3.sup.6 =A.sub.11 -A.sub.12
C.sub.3.sup.7 =A.sub.13 -A.sub.14
C.sub.3.sup.8 =A.sub.15 -A.sub.16
C.sub.2.sup.1 =(A.sub.1 +A.sub.2)-(A.sub.3 +A.sub.4)
C.sub.2.sup.2 =(A.sub.5 +A.sub.6)-(A.sub.7 +A.sub.8)
C.sub.2.sup.3 =(A.sub.9 +A.sub.10)-(A.sub.11 +A.sub.12)
C.sub.2.sup.4 =(A.sub.13 +A.sub.14)-(A.sub.15 +A.sub.16)
C.sub.1.sup.1 =(A.sub.1 +A.sub.2 +A.sub.3 +A.sub.4)-(A.sub.5 +A.sub.6 +A.sub.7 +A.sub.8) C.sub.1.sup.2 =(A.sub.9 +A.sub.10 +A.sub.11 +A.sub.12)-(A.sub.13 +A.sub.14 +A.sub.15 +A.sub.16)
C.sub.o.sup.1 =(A.sub.1 +A.sub.2 +. . . +A.sub.8)-(A.sub.9 +A.sub.10 + . . . +A.sub.16)
and C.sub.o =A.sub.1 +A.sub.2 + . . . +A.sub.16 These results may be easily verified from Eqs. (10) and (14).
From block 310, system operation proceeds to block 312 (FIG. 10B) for commencement of the derivation of additional parameters for the signature vector based upon selection and manipulation of certain physical features of the signature waveform. A number of different such physical features can be utilized if desired, and while the features chosen for use in the device described herein are suitable to provide a satisfactory signature vector, it should be recognized that other features of the signature waveform could also be enployed. Also, if a less precise standard of signature verification is adequate for certain applications, the use of some or all physical features in the signature vector could be omitted, so that only parameters based upon Haar coefficients could be employed.
The following physical features have been selected for use in the illustrated embodiment: signature time, pen lift time, pin lift number, slope change and peak. These are defined as follows:
Signature time is the total number of digitized samples obtained from the signature.
Pen lift time is the total number of samples taken during the time that the writing instrument is not in contact with the writing surface during the act of signing.
Pen lift number is the number of times that the writing instrument is not in contact with the writing surface during the act of signing.
Slope change is a change in the signature waveform from positive slope to negative slope.
Peak is a value corresponding to the number of times in a signature that there is one and only one slope change between two pen lifts.
In generation of a signature vector, two groupings of physical features are considered. A total of twenty-two different parameters, as described below, are provided from these physical features.
The first of the two groups provides six parameters from measures that relate to the overall force pattern of the signature, as follows:
P16 is the total signature time.
P17 is the average force applied.
P18 is the total pen lift time.
P19 is the total number of pen lifts.
P20 is the total number of slope changes.
P21 is total number of peaks.
The second of the two groups contains measures that are obtained by dividing the total signature time into a number of equal time intervals. Four such intervals, such as those designated A, B, C and D in FIG. 3D, appear to provide best results. It may also be noted that in FIG. 3D, the total signature time is designated TS, and the pen lift times are designated PL1, PL2 and PL3. The following parameters measure quantities as described below, each parameter within a category being for one of the four equal intervals.
P22 to P25 are the pen lift time parameters during each interval.
P26 to P29 are number of pen lifts per interval.
P30 to P33 are the number of slope changes per interval.
P34 to P37 are the number of peaks per interval.
In block 312, all of the quantities shown therein are initialized. F, referring to the time interval number in the waveform, is set equal to zero. I, referring to the entry or index number for TABLE 1 and TABLE 2, is set equal to zero. NKX is set equal to the number of entries in TABLE 1 and TABLE 2. Physical feature parameters P16 to P37 inclusive are set equal to zero. An arbitrary value VAL, to be subsequently described, is set equal to zero. A pen lift region indicator ZFLG is set equal to zero. An indicator IFLG, which indicates transition between intervals, is set equal to zero. A peak indicator PKFLG is set equal to zero.
In block 314, a quantity T stored in an appropriate location in memory 80 is set equal to the value of the last entry in TABLE 2, which corresponds to the total number of samples in the signature.
System operation then proceeds to block 316, wherein time interval number F is set equal to F+1, and the upper limit in number of samples in the new interval is computed according to the expression ILIM(F)=(T.F./4). Following this, as shown in block 318, the entry number I is incremented by one. The system operation then proceeds to decision block 320, in which I is compared to NKX. Since in the initial operation, I will not be greater than NKX, operation proceeds to decision block 322, in which the current entry I of TABLE 2 is compared to ILIM(F). In the initial operation, TABLE 2 (I), will be less than ILIM(F), and the system operation proceeds to decision block 324, in which the current entry I of TABLE 1 is compared to the quantity VAL. Originally, TABLE 1 entry I will not be equal to or less than VAL, and therefore operation continues to block 326, in which the quantity VAL is set equal to the entry I of TABLE 1.
System operation then loops back over path 328 to block 318, in which I is again incremented by one. Operation then continues through blocks 320, 322 and 324. The comparison made in block 324 now shows that TABLE 1 entry I is less than VAL since the signature waveform has a negative slope at this point. Therefore operation proceeds to decision block 330, where ZFLG is compared to one. Since ZFLG was initially set equal to zero, operation proceeds to block 332, where a number of actions take place. PKFLG is incremented by one. The quantity VAL is set equal to zero. The parameter P20 is incremented by one, as is the quantity P(29+F). Operation then proceeds to decision block 334, where the I entry of TABLE 1 is compared to zero. If this quantity is not equal to zero, operation loops back over path 328 to block 318. If this quantity is equal to zero, the operation proceeds to block 336 (FIG. 10C), where a quantity STZ, representing the starting sample number of a pen lift is set equal to entry I of TABLE 2, and a quantity ENZ, representing the ending sample number of the pen lift, is set equal to entry (I+1) of TABLE 2. Also the quantity ZFLG is set equal to one.
Operation then proceeds to decision block 338, where the quantity PKFLG is compared to one. If PKFLG equals one, parameter P21 is set equal to P21+1 and the quantity P(33+F) is set equal to P(33+F)+1, and these two quantities are stored in memory location 98 of memory 80 (FIG. 5), as shown in block 340. Operation then loops back over path 328 to block 318. If PKFLG is not equal to one, operation loops directly from block 338 to block 318 over path 328.
Now let it be assumed that when system operation has proceeded to decision block 330 (FIG. 10B), ZFLG is found to be equal to one. In such case, operation proceeds to block 342 (FIG. 10C), where the quantities ZFLG and PKFLG are set equal to zero, and then continues to decision block 344 where IFLG is compared to one. Let it also be assumed that IFLG, representing the between intervals indicator, is equal to zero, and therefore not equal to one, indicating that there has been no change in the interval. In such case, the pen lift quantity PL is set equal to one as shown in block 346 and operation proceeds to block 350. On the other hand, if the interval has changed, so that IFLG is equal to one, operation proceeds to block 348, where PL is set equal to one minus the previous value stored in PL, IFLG is set equal to zero, and operation then proceeds to block 350.
In block 350, PLS, representing the number of pen lift samples, is set equal to ENZ minus STZ. Also, parameter P19 is set equal to P19 +PL and the result is stored; quantity P(2+5F) is set equal to P(25+F)+PL and the result is stored; P18 is set equal to P18 +PLS and the result is stored; and the quantity P(21+F) is set equal to P(21+F)+PLS and the result is stored. All such storage is in location 98 of memory 80 (FIG. 5). System operation then loops back over path 328 to block 318.
Now let it be assumed that when system operation has proceeded to decision block 322 (FIG. 10B), the I entry of TABLE 2 is found to be greater than ILIM(F). In such case, operation proceeds over path 323 to decision block 352, (FIG. 10D), where the quantity ZFLG is compared to one. If ZFLG is not equal to one, the current I entry in TABLE 2 is not in a pen lift region and operation continues with the decrementing by one of I, as shown in block 354, after which the system operation loops back over path 355 to block 316 (FIG. 10B). If ZFLG is equal to one, operation proceeds to block 356. ENZ is set equal to ILIM(F); PL is set equal to ILIM(F)/TABLE 2 (I)-TABLE 2 (I-1); and PLS is set equal to ENZ minus STZ. The following values are computed in accordance with the following assignments and stored in memory location 98 (FIG. 5):
P19=P19 +PL
P(25+F)=P(25+F)+PL
P18=P18+PLS
P(21+F)=P(21+F)+PLS.
In addition, the following quantities are computed and put in temporary storage:
STZ=ILIM(F)+1
ENZ=TABLE 2 (I)
IFLG=1.
Following this, system operation loops back to block 354.
Now let it be assumed that when system operation has proceeded to decision block 320, (FIG. 10B), the current I entry is found to be greater than NKX. In such case, operation proceeds to block 358 (FIG. 10B), where average force is computed by dividing the quantity SUM (see block 164 of FIG. 4A) by T, which was computed in block 314. In addition, the value T is stored in location 98 as parameter P16, and the value AVE is stored in location 98 as parameter P17.
From block 358, system operation returns over path 360 to block 362 of FIG. 7B, it being noted that by means of the operations of FIGS. 10A, 10B, 10C and 10D, all of the parameters of a signature vector for a given signature (J) have been derived and stored in location 98 (FIG. 5). This signature vector is now stored in the appropriate memory location 96, as shown in block 362, FIG. 7B.
System operation then proceeds to decision block 364, and is caused to loop repetitively over path 366 through blocks 274, 278, 302 and 362 until five signature vectors have been derived and stored in memory location 96. When J is found to be equal to five in block 364, operation proceeds over path 368 to block 370 (FIG. 7A), in which a reference for a given person is generated.
The operation represented generally in block 370 is shown in greater detail in FIG. 14. It will be recalled that for each signature vector P1 to P5 inclusive, there are thirty-seven components P.sub.j,r where j equals 1 to 5 inclusive and r equals 1 to 37 inclusive.
As shown in block 374 of FIG. 14, an average vector P, representing an average of the five signature vectors and having thirty-seven components P.sub.r, is computed in accordance with the equation contained in block 374, and is stored in memory location 92 of the memory 80 (FIG. 5). Following this, a single variance vector V is computed, utilizing all of the signature vectors P1 to P5, together with the average vector P, as shown in block 376, in accordance with the equation contained therein, and is placed in a temporary storage location.
Next, as shown in block 378, a normalizing vector Q is computed and is stored in memory location 92 of memory 80 (FIG. 5). The normalizing vector Q comprises thirty-seven components Q.sub.r, where each component Q.sub.r is computed in accordance with one of the three equations appearing in block 378, depending in each case upon the values of four quantities B.sub.r, P.sub.r, SP.sub.r and V.sub.r.
The quantities SP.sub.r and B.sub.r are individual components of modifiers SP and B, where r=1, 2, 3-37; where SP is an average vector derived from signatures of different people in a sample population tested; and where B is a variance vector derived from comparison of signatures of different people in said sample population from the average.
Due to the small statistical significance that can be given to the estimation of parameters from the five signatures used during the reference procedure, it is necessary to modify the variance vector V for person "k", for those components which present large deviations from the corresponding values obtained for the overall population tested.
In the illustrated embodiment, the vectors B and SP are generated from signature vectors collected for fifty persons. These vectors are generated only one time during the system design phase. They then are part of the global data area of the reference mode program and are loaded into memory as a part of said program.
The modified variance vector for person "k" is called the normalizing vector Q.
A method for generating vectors B and SP is shown in FIGS. 15A and 15B, and the process illustrated therein will now be described.
As shown in block 380 (FIG. 15A), the quantity k representing the person number, where it will be recalled that k equals 1, 2, 3-50, is set equal to zero. The quantities SB.sub.r and SSP.sub.r, representing sums of quantities B.sub.r and SP.sub.r, respectively, are also set equal to zero. It will be recalled that r equals 1, 2, 3-37.
The process then proceeds by setting k equal to k+1, as shown in block 382, and continues to decision block 384, where k is compared to the quantity fifty-one. Since at this point in the process, k is not equal to fifty-one, the process continues to block 386, where signature number j is initialized to zero, and subsequently is incremented by one, as shown in block 388.
In the next step, a comparison is made in block 390 as to whether j is equal to six. Assuming it is not, a signature j is obtained in block 392, a waveform is derived therefrom in block 394, TABLE 1 and TABLE 2 are computed in block 396, and a signature vector P.sub.k,j is computed and saved in temporary storage in block 398 (FIG. 15B). It will be recognized that these steps are essentially the same as those described elsewhere for obtaining a signature vector, except that no time normalizing takes place. This process is continued until five signature vectors have been obtained, after which the process takes a path from decision block 390 to a block 400 (FIG. 15A), in which an average signature vector P.sub.k is obtained in a conventional averaging process and saved in temporary storage.
Next, as shown in block 402, the sum SSP.sub.r, is computed by adding the last derived quantity P.sub.k,r to the previous sum SSP.sub.r, where P.sub.k,r is the "R" component of P.sub.k, where r=1, 2-37. In block 404 (FIG. 15B), the sum SB.sub.r is computed in accordance with the equation contained therein.
The process then loops back over path 406 to block 382, where the quantity k is incremented by one, and then proceeds to decision block 384, from whence the process continues until signatures have been obtained from fifty people, after which the process proceeds over path 407 to block 408 (FIG. 15B). In that block, the quantities SP.sub.r and B.sub.r are computed in accordance with the equations found therein. The modifiers SP and B, comprised of all of the "r" components of SP.sub.r and B.sub.r, are then stored in permanent storage locations 97 and 99 of memory 80 (FIG. 5), as indicated in block 410.
Now, returning to block 378 of FIG. 14, the normalizing vector Q is computed as previously described, following which, in block 412, an error quantity E.sub.j is computed for each of the five signature vectors which have been obtained, in accordance with the equation appearing therein. A threshold value T is then computed in accordance with the equation shown in block 414. In the illustrated embodiment, a value of 4 has been assigned to the quantity KT, which is a constant by which the average error is multiplied to provide a threshold value.
From block 414, the process returns over path 372 to the reference mode diagram of FIG. 7A. Since the next block 416 of FIG. 7A, designated "ANALYZE SIGNATURE VECTORS", represents another complex group of operations, it is shown in detail in FIG. 16, in which the path 372 continues to the operation shown in block 418. In this operation, the error values E.sub.j, which were computed in block 412, are sorted and placed in ascendant order with respect to magnitude of error, with the smallest error being designated E.sub.h1 and the largest error being designated E.sub.h5. In addition, a record is kept in temporary storage of the relationship of the signature number j to the relative magnitude of error h. Thus, j.sub.1, for example, would correspond to h.sub.3 if the error in the first signature vector were the third greatest in magnitude.
Next, an acceptance value EVS is computed in accordance with the equation shown in block 420, equal to two times the average of the three lowest error values. This value EVS is compared in decision block 422 to the error value E.sub.h4.
If the value E.sub.h4 exceeds EVS, then it is known that both of the signatures corresponding to E.sub.h4 and E.sub.h5 exceed the maximum permissible error. As shown in block 424, the signatures corresponding to E.sub.h4 and E.sub.h5 are determined, using the record generated in block 418, and the corresponding j values are placed in temporary storage.
If the value E.sub.h4 does not exceed the value EVS in the comparison made in decision block 422, a further comparison is made in block 426 to determine whether the value E.sub.h5 exceeds the value EVS. If not, an indication is provided by block 430 that five acceptable signatures are present. However if E.sub.h5 exceeds EVS, then it is known that the signature corresponding to E.sub.h5 exceeds the maximum permissible error. As shown in block 428, the signature corresponding to E.sub.h5 is determined, using the record generated in block 418, and the corresponding j value is placed in temporary storage.
The reference process then returns from FIG. 16 back to FIG. 7A over path 432 and proceeds to decision block 434, where a determination is made as to whether or not additional signatures are required, in accordance with the information stored from operations defined in blocks 424, 428 and 430 of FIG. 16.
Let it be assumed that no additional signatures are required. In such case, the process proceeds over path 436 to block 438 (FIG. 7B) in which the previously generated quantities, average signature vector P.sub.k, the normalizing vector Q.sub.K and the threshold value T.sub.k are taken from memory location 92 (FIG. 5) and permanently stored on reference disk unit 94 (FIGS. 5 and 7B) which is part of storage unit 116 (FIG. 1). This completes the system operation of the reference mode, as indicated by block 439.
If, on the other hand, additional signatures are required, system operation proceeds from decision block 434 to block 440, in which the number of times "W" that a customer is permitted to replace invalid signatures is incremented by one. In decision block 442, the new quantity W is compared to the quantity five. If five signature replacements have already been made, operation proceeds over path 444 to the end of the reference mode operation, as represented by block 439. This limitation of number of signature replacements is provided in order to prevent the unusual situation from arising in which an indefinite number of replacement signatures would be called for by the system operation.
If additional signatures are required, and fewer than five replacements have been made, the operation proceeds to block 446, in which the number "J" of the invalid signature is identified, and a new signature J is obtained in block 448 by having the customer write his signature on the unit 108 (FIG. 1). In the same manner as previously described, the forces generated by writing the signature are converted to a waveform and digitized in block 450, and TABLE 1 and TABLE 2 for signature J are computed in block 452. These table values then replace the previous values for signature J in memory location 86 (FIG. 5) as indicated in block 454.
Operation then proceeds to the decision block 456 (FIG. 7B), in which a determination is made as to whether or not all of the invalid signatures have been replaced. If not, the operation loops back over path 458 to block 446, so that the remaining invalid signature can be replaced.
Once all of the invalid signatures have been replaced, operation proceeds from decision block 456 to block 238, so that the signature vectors for the five signatures now stored in location 86 can be computed and saved, as previously described in connection with blocks 238, 272, 274, 278, 302 and 362.
The process then again loops over path 368 to block 370 for generation of the reference values P.sub.k, Q.sub.K and T.sub.k, as previously described. The signature vectors are then analyzed again, as indicated by block 416, to determine whether any invalid signatures are present in this new group of signatures. A determination is then made once more in block 434 so as to determine whether any additional signatures are required. If not, as previously described, the new reference values P.sub.k, Q and T.sub.k are stored on reference disk 94. If so, an additional operation may be required, as previously described, unless five replacements have already been made, in which case reference mode operation is terminated in any event.
Once the reference parameters for a particular individual "k" have been computed and placed in secondary storage on reference disk 94, the identity of that person "k" can be verified whenever desired by comparing a signature vector generated by his or her writing a signature on the unit 108 with the reference parameters so stored.
Returning to the generalized flow diagram of FIGS. 2A, 2B and 2C, it will be recalled that the verify mode is entered at block 126, at which time the system is ready to accept an identity claim number (ID#) from the key pad unit 114, as indicated by the lead-through unit 104, on which the "verify" and "ID#" indicators are on. The customer then enters the ID# assigned to him or her, which shall be designated as "k", on the key-pad unit 114. Follwing this, the ID# indicator is turned off.
Since it will be assumed for purpose of this description that the ID# entered is not the special reference code (999 for purpose of illustration), as determined in block 128, the reference parameters are fetched from disk 94 and placed in storage location 92, as shown in FIG. 5. An audible tone from unit 106 and a "sign" indicator on unit 104 then indicate to the customer that a signature should be made on unit 108. After the customer provides the signature, the "sign" indicator of unit 104 goes off, and the record medium on which the signature has been made is advanced by unit 112.
Following this, a signature vector is computed as shown in block 460, and compared with the average signature vector P.sub.k as shown in block 462. An error value is derived from this comparison, and by use of the normalizing vector Q.sub.K. This error quantity is then compared in block 464 with the threshold value T.sub.k.
If the error value is less than the threshold value, the "accept" indicator of the unit 104 is turned on, and the reference parameters for that customer are updated. The identity of the customer has thus been verified, and the system may control other apparatus or additional transaction steps to permit customer entry thereto.
On the other hand, if the error value is larger than the threshold value, the "reject" indicator of the unit 104 is turned on. The identity of the customer in this case has not been verified, and access of the customer to other apparatus or additional transaction steps may be denied.
A detailed description of the operation of the system in the verification mode will now be provided, in connection with the flow diagram of FIGS. 17A and 17B.
System operation in the verify mode is commenced by entering an ID# 37 k" into the keyboard unit 114. This number is saved in an appropriate location in storage, as indicated in block 470.
The reference parameters P.sub.k, Q.sub.k and T.sub.k are then fetched from their location on reference disk 94 and are stored in location 92 of memory 80, as indicated by block 472.
The customer is then directed in block 474 to make a signature on unit 108, which converts said signature to digital voltage samples in block 476. TABLE 1 and TABLE 2 are computed from said samples in block 478, utilizing the process shown in FIGS. 4A, 4B, as previously described, and stored in location 86 of memory 80 (FIG. 5), for J equals 1, as represented in block 480.
Following this, time normalizing parameters RT, RPL and RPLS, representing the average of the total signature time, the average of the total number of pen lifts and the average of the total pen lift times, respectively, are taken from the average signature vector P which is stored in location 92, as indicated in block 482. The parameters RT, RPL and RPLS are equal to the physical features P16, P19 and P18, respectively, which constitute components of the average signature vector P.
As represented by block 484, TABLE 1 and TABLE 2 for J equals 1 are then transferred to location 88 and normalized in accordance with the process shown in detail in FIG. 9 and previously described, and saved in location 90.
The system operation then continues as represented in block 486 by computing a signature vector for the signature being tested, in the manner previously described in connection with FIGS. 10A to 10D inclusive. This signature vector is saved (block 488) in location 96 of memory 80 (FIG. 5) as signature vector P1.
As the next step in system operation, the error value for this signature is computed in block 490, in accordance with the equation contained therein. It will be noted that this computation is similar to the computation performed in block 412 of FIG. 14. In the equation of block 490, E.sub.k is the error value for the signature of person "k"; P.sub.k,r is the "r" component of the signature vector P for the signature of person k; P.sub.k,r is the "r" component of the average signature vector P for the reference signatures of person k; and Q.sub.k,r is the "r" component of the normalizing vector Q for the reference signatures of person k.
After the error value E.sub.k has been obtained, system operation proceeds to decision block 492 (FIG. 17B) in which the error value E.sub.k is compared to the reference threshold value T.sub.k. Let it be assumed that the error value E.sub.k is less than the threshold value T.sub.k. In such case, the identity claim is accepted, as indicated in block 494 to enable the next desired transaction to take place, and the "ACCEPT" light on lead-through unit 104 is illuminated, as indicated in block 496.
Following this, the value E.sub.k is compared to onehalf of the threshold value T.sub.k as shown in decision block 498. If E.sub.k is not equal to or less than T.sub.k/2, the verification process is completed, as indicated by path 500 proceeding to "EXIT" block 502. However, if E.sub.k is equal to or less than T.sub.k/2, then this signature vector is used to update the reference vectors P.sub.k and Q.sub.k.
In such case, system operation proceeds to block 504, where "r" is set equal to zero and a quantity L, representing a weighting factor, is set equal to 20. In block 506, "r" is incremented by one, following which, in block 508, the new values for P.sub.k,r and Q.sub.k,r are computed in accordance with the equations set forth therein.
System operation then proceeds to decision block 510, where the numerical value of "r", representing the component number of vectors P.sub.k and Q.sub.k, is compared to 37, which is the total number of such components. System operation loops back over path 512 to block 506, and continues to do so until values P.sub.k and Q.sub.k have been computed for each of the 37 components, at which time the system operation proceeds to block 514 in which updated reference values P.sub.k and Q.sub.k, together with the existing value T.sub.k, are stored on the disk 94. The verification process is thereby completed as indicated by block 502.
Returning to decision block 492, it will be noted that in the event that the error value E.sub.k for signature k is not less than the threshold value T.sub.k, the identity claim is rejected as indicated in block 516, so that further transactions may be prevented, and the "REJECT" light on lead-through unit 104 is illuminated, as shown in block 518. The verification operation is completed, as indicated by path 500 to EXIT block 502.
Included as an attached appendix is a group of program listings in Intel 8080 assembly language for the system operations described above, together with other included functions, such as gathering of experimental data relating to signature samples, testing and analyzing, which are not directly pertinent to the present invention.
While the form of the invention shown and described herein is admirably adapted to fulfill the objects aforesaid, it is to be understood that other and further modifications of the disclosed method and apparatus within the scope of the following claims may be made without departing from the spirit of the invention. For example, an implementation to be utilized in a system having relatively lower security requirements might omit certain portions of the processing procedures disclosed herein. ##SPC1## ##SPC2## ##SPC3## ##SPC4## ##SPC5## ##SPC6## ##SPC7## ##SPC8## ##SPC9## ##SPC10## ##SPC11##

Claims

1. A method for verifying the identity of a person from samples of handwriting comprising the steps of
A. converting forces generated from writing a signature by the person whose signature is to be verified to an electrical signal representative thereof;
B. generating a digital representation of said signal;
C. deriving an information vector from the digital representation of the signature of the person whose identity is to be verified;
D. providing identification indicia assigned to the person whose signature is to be verified;
E. comparing said information vector with a unique reference vector associated with said identification indica provided for said person to derive an error value representing the variance between the two vectors;
F. comparing said derived error value with a unique threshold value associated with the identification indicia provided for said person; and
G. providing indication of acceptance if the derived error value is less than the unique threshold value and providing indication of rejection if the derived error value is greater than the unique threshold value.
2. The method of claim 1, also including the step of updating the reference vector if the handwriting sample being tested is accepted, by utilizing said accepted information vector to derive a new reference vector.
3. A method for verifying the identity of the writer of a signature by comparing a signal generated from the writing of said signature with a known reference value, comprising
A. providing identification indicia to select a reference vector and a threshold value which have been predetermined for the person whose identity is to be verified;
B. converting forces generated from writing a signature by the person whose identity is to be verified to an electrical signal representative thereof;
C. generating a digital representation of said signal;
D. deriving a signature vector from said digital representation;
E. determining the amount of deviation between said signature vector and the reference vector;
F. comparing the amount of deviation with the threshold value; and
G. indicating verification of identity if the amount of deviation is less than the threshold value and rejection of identity if the amount of deviation is greater than the threshold value.
4. The method of claim 3, also including the step of updating the reference vector if verification of identity is indicated, by utilizing said accepted information vector to derive a new reference vector.
5. A method for verifying the identity of the writer of handwritten information by comparing a signal generated from the writing of said information with a known reference value, comprising
generating a digital representation of said signal;
deriving an information vector from said digital representation including deriving a plurality of Haar coefficients;
comparing said information vector derived from said handwritten information with information derived from previous handwriting samples of the person whose identity is to be verified to determine whether or not the identity of the writer is verified; and
updating the information derived from previous handwriting samples if the identity of the writer is verified, by utilizing said information vector to revise the information derived from previous handwriting samples.
6. The method of claim 5 in which the step of deriving an information vector from the digital representation includes deriving a plurality of physical features in addition to the plurality of Haar coefficients.
7. The method of claim 6 in which said plurality of physical features includes a first group of features representative of the digital representation as a whole and a second group of features representative of each of a plurality of portions of said digital representation.
8. The method of claim 5 in which the comparing step includes determining whether the amount of deviation between the information vector for the writing of the person whose identity is being tested and the reference information vector exceeds a predetermined permissible amount.
9. The method of claim 5 in which the comparing step includes first determining the amount of deviation between said information vector and a reference vector, and also then comparing said amount of deviation with a predetermined deviation amount unique to said person.
10. A method for deriving an information vector for verifying the identity of a person from a handwriting sample, comprising the steps of
A. deriving an analog electrical signal from forces measured during the writing of the sample;
B. digitizing said analog signal;
C. compressing the digitized signal;
D. extracting Haar coefficients and directly observable features from the compressed digital signal; and
E. deriving an information vector from said Haar coefficients and said directly observable features.
11. The method of claim 10 in which the directly observable features include a first group of features representative of the compressed digital signal as a whole and a second group of features representative of each of a plurality of portions of said compressed digital signal.
12. The method of claim 10 in which the compressing step includes time-normalizing the signal to minimize the effect of those signal levels resulting from pen lift segments included in the act of providing the handwriting sample.
13. A machine-implemented method for deriving a standard for verifying the identity of a person from handwritten signatures, comprising the steps of
A. providing a plurality of handwriting samples of the same informational content of a person for whom a reference information vector is desired;
B. providing an electrical signal representative of each of said plurality of handwriting samples;
C. deriving an individual signature vector from each one of said plurality of electrical signals;
D. storing said signature vector;
E. computing an average vector from said plurality of individual signature vectors;
F. computing an individual error value for each signature vector based on a comparison of each signature vector with the average vector;
G. computing an average error value using at least some of said individual error values;
H. computing an acceptance error value based upon said average error value;
I. comparing said individual error values with said acceptance error value;
J. discarding any individual signature vector having an error value in excess of the acceptance error value;
K. providing additional handwriting samples for deriving additional individual signature vectors to replace those discarded;
L. computing individual error values for said additional individual signature vectors;
M. comparing said additional individual error values with said acceptance error value and repeating steps A to J inclusive until a predetermined number of acceptable individual signature vectors have been obtained;
N. computing a revised average signature vector from the acceptable individual signature vectors;
O. computing revised individual error values for each acceptable individual signature vector based on a comparison of each revised individual signature vector with the revised average signature vector;
P. computing a threshold value based upon the revised individual error values;
Q. computing a normalizing vector assigning different weights to different aspects of the revised average information vector in accordance with the degrees of consistency of said different aspects in the various individual signature vectors;
R. computing a reference vector based upon the revised average signature vector and the normalizing vector; and
S. maintaining the threshold value and the reference vector to be utilized jointly as a standard for use in evaluating a vector derived from a handwritten signature of a person whose identity is to be verified.
14. The method of claim 13 in which step C includes the steps of
C1. digitizing said electrical signal;
C2. compressing the digital signal;
C3. time-normalizing the compressed digital signal;
C4. extracting Haar coefficients and directly observable features from the compressed and time-normalized digital signal; and
C5. deriving an individual signature vector from said Haar coefficients and said directly observable features.
15. A machine-implemented method for deriving a standard for verifying the identity of a person from samples of handwriting, comprrising the steps of
A. providing a plurality of handwriting samples of the same informational content of a person for whom a reference information vector is desired;
B. providing an electrical signal representative of each of said plurality of handwriting samples;
C. deriving an individual information vector from each one of said plurality of electrical signals;
D. computing an average information vector from said plurality of individual information vectors;
E. computing individual error values and an average error value indicative of deviation of said individual information vectors from said avverage information vector;
F. computing an acceptance error value based upon said average error value;
G. discarding any individual information vector having an error value in excess of the acceptance error value;
H. providing and testing additional individual information vectors until a predetermined number of acceptable individual information vectors have been obtained;
I. computing a revised average information vector and revised individual error values from the acceptable individual information vectors;
J. computing a threshold value based upon the revised individual error values;
K. computing a normalizing vector which assigns different weights to different aspects of the revised average information vector;
L. computing a reference vector based upon the revised average information vector and the normalizing vector; and
M. providing a verification standard comprising the threshold value and the reference value to be used jointly in evaluating a vector derived from a handwriting sample of a person whose identity is to be verified.
16. The method of claim 15 in which step C includes the steps of
C1. digitizing said analog signal;
C2. compressing the digital signal;
C3. extracting Haar coefficients and directly observable features from the compressed digital signal; and
C4. deriving an individual information vector from said Haar coefficients and said directly observable features.
17. A machine-implemented method for deriving a standard for verifying the identity of a person from samples of handwriting, comprising the steps of
A. providing a plurality of handwriting samples of the same information content of a person for whom a reference information vector is desired;
B. providing an electrical signal representative of each of said plurality of handwriting samples;
C. deriving an individual information vector from each one of said plurality of electrical signals;
D. computing an average information vector from said plurality of individual information vectors;
E. computing individual error values and an average error value indicative of deviation of said individual information vectors from said average information vector;
F. computing an acceptance error value based upon said average error value;
G. computing a threshold value based upon the individual error values;
H. computing a normalizing vector which assigns different weights to different aspects of the average information vector;
I. computing a reference vector based upon the average information vector and the normalizing vector; and
J. providing a verification standard comprising the threshold value and the reference value to be used jointly in evaluating a vector derived from a handwriting sample of a person whose identity is to be verified.
18. Apparatus for verifying the identity of a writer of handwritten information by comparing a signal generated from the writing of said information with a known reference, comprising
manually operable means for inputting identification indicia to select a unique reference vector and a unique threshold which have been predetermined for the person whose identity is to be verified;
pressure-responsive transducer means for converting forces generated from writing said information to an analog signal representative thereof;
analog-to-digital converter means for generating a digital representation of said signal;
means for deriving an information vector from said digital representation;
means for determining the amount of deviation between said information vector and the reference vector for said person;
comparing means for comparing the amount of deviation with the unique threshold for said person; and
indicator means controlled by said comparing means for indicating verification of identity if the amount of deviation is less than the unique threshold and for indicating rejection of identity if the amount of deviation is greater than the unique threshold.
19. The apparatus of claim 18, also including means for updating the selected reference vector by recomputing said vector using the information vector derived from said handwritten information provided by the writer in the event that verification of identity is indicated.
20. Apparatus for verifying the identity of a writer of handwritten information by comparing a signal generated from the writing of said information with a known reference value, comprising
pressure-responsive transducer means for converting forces generated from writing said information to an analog electrical signal representative thereof;
analog-to-digital converter means for generating a digital representation of said signal;
means for deriving an information vector from said digital representation including a plurality of Haar coefficients and a pluarlity of physical features; and
means for comparing said information vector derived from said handwritten information with information derived from previous handwriting samples of the writer whose identity is to be verified to determine whether or not the identity of the writer is verified.
21. The apparatus of claim 20 in which said plurality of physical features includes a first group of features representative of the digital representation as a whole and a second group of features representative of each of a plurality of portions of said digital representation.
22. The apparatus of claim 20 in which the comparing means includes error means for determining the permissible amount of deviation between the information vector for the writing of the person whose identity is being tested and the reference information vector.
23. The apparatus of claim 20 in which the comparing means includes first means for determining the amount of deviation between said information vector and a reference vector, and also includes second means for comparing said amount of deviation with a predetermined deviation amount unique to said person.
24. The apparatus of claim 20, also including means for updating said information derived from previous handwriting samples by recomputing said information using the information vector derived from said digital representation in the event that verification of identity is indicated.
25. Apparatus for deriving a standard for verifying the identity of a person from handwritten signatures, comprising
means for deriving an individual signature vector from each one of a plurality of handwriting samples of the same informational content of a person for whom a reference information vector is desired;
means for storing each said signature vector;
means for computing an average vector from said plurality of individual signature vectors;
means for computing an individual error value for each signature vector based on a comparison of each signature vector with the average vector;
means for computing an average error value using at least some of said individual error values;
means for computing an acceptance error value based upon said average error value;
means for comparing said individual error values with said acceptance error value;
means for discarding any individual signature vector having an error value in excess of the acceptance error value;
means for requesting additional handwriting samples for deriving additional individual signature vectors to replace those discarded;
means for computing individual error values for said additional individual signature vectors;
means for comparing said additional individual error values with said acceptance error value;
means for effecting the generation and testing of additional individual signature vectors until a predetermined number of acceptable individual signature vectors have been obtained;
means for computing a revised average signature vector from the acceptable individual signature vectors;
means for computing revised individual error values for each acceptable individual signature vector based on a comparison of each revised individual signature vector with the revised average signature vector;
means for computing a threshold value based upon the revised individual error values;
means for computing a normalizing vector assigning different weights to different aspects of the revised average signature vector in accordance with the degrees of consistency of said different aspects in the various individual signature vectors;
means for computing a reference vector based upon the revised average signature vector and the normalizing vector; and
means for maintaining the threshold value and the reference value to be utilized jointly as a standard for use in evaluating a vector derived from a handwritten signature of a person whose identity is to be verified.
26. The apparatus of claim 25 in which the means for deriving includes means for producing an analog electrical signal from forces measured during the writing of the sample;
means for digitizing said analog signal;
means for compressing the digital signal;
means for extracting Haar coefficients and directly observable features from the compressed digital signal; and
means for assembling an individual signature vector from said Haar coefficients and said directly observable features.
27. The apparatus of claim 26 in which the directly observable features include a first group of features representative of the compressed digital signal as a whole and a second group of features representative of each of a plurality of portions of said compressed digital signal.
28. Apparatus for deriving a standard for verifying the identity of a person from samples of handwriting, comprising
means for deriving an individual information vector from each one of a plurality of handwriting samples of the same informational content of a person for whom a reference information vector is desired;
means for computing an average information vector from said plurality of individual information vectors;
means for computing individual error values and an average error value indicative of deviation of said individual information vectors from said average information vector;
means for computing an acceptance error value based upon said average error value;
means for computing a threshold value based upon the individual error values;
means for computing a normalizing vector which assigns different weights to different aspects of the average information vector;
means for computing a reference vector based upon the average information vector and the normalizing vector; and
means for providing a verification standard comprising the threshold value and the reference value to be used jointly in evaluating a vector derived from a handwriting sample of a person whose identity is to be verified.
29. Apparatus for deriving a standard for verifying the identity of a person from samples of handwriting, comprising
means for deriving an individual information vector from each one of a plurality of handwriting samples of the same informational content of a person for whom a reference information vector is desired;
means for computing an average information vector from said plurality of individual information vectors;
means for computing individual error values and an average error value indicative of deviation of said individual information vectors from said average information vector;
means for computing an acceptance error value based upon said average error value;
means for discarding any individual information vector having an error value in excess of the acceptance error value;
means for providing and testing additional individual information vectors until a predetermined number of acceptable individual information vectors have been obtained;
means for computing a revised average information vector and revised individual error values from the acceptable individual information vectors;
means for computing a threshold value based upon the revised individual error values;
means for computing a normalizing vector which assigns different weights to different aspects of the revised average information vector;
means for computing a reference vector based upon the revised average information vector and the normalizing vector; and
means for providing a verification standard comprising the threshold value and the reference to be used jointly in evaluating a vector derived from a handwriting sample of a person whose identity is to be verified.
30. The apparatus of claim 29 in which the means for deriving includes
means for producing an analog electrical signal from forces measured during the writing of the sample;
means for digitizing said analog signal;
means for compressing the digital signal;
means for extracting Haar coefficients and directly observable features from the compressed digital signal; and
means for assembling an individual information vector from said Haar coefficients and said directly observable features.
31. The apparatus of claim 30 in which the directly observable features include a first group of features representative of the compressed digital signal as a whole and a second group of features representative of each of a plurality of portions of said compressed digital signal.
32. Apparatus for deriving an information vector for verifying the identity of a person from a handwriting sample, comprising
transducer means for deriving an analog electrical signal from forces measured during the writing of the sample;
means for digitizing said analog signal;
means for compressing the digitized signal;
means for extracting Haar coefficients and directly observable features from the compressed digital signal; and
means for deriving an information vector from said Haar coefficients and said directly observable features.
33. The apparatus of claim 32 in which the directly observable features include a first group of features representative of the compressed digital signal as a whole and a second group of features representative of each of a plurality of portions of said compressed digital signal.

US Referenced Citations (24)

Number	Name	Date
3145367	Crane	Aug 1964
3462548	Rinder	Aug 1969
3480911	Danna	Nov 1969
3579186	Johnson et al.	May 1971
3618019	Nemirovsky et al.	Nov 1971
3621720	Clark	Nov 1971
3818443	Radcliffe, Jr.	Jun 1974
3859515	Radcliffe, Jr.	Jan 1975
3906444	Crane et al.	Sep 1975
3950733	Cooper et al.	Apr 1976
3956734	Radcliffe, Jr.	May 1976
3959769	Sternberg et al.	May 1976
3962679	Engelbrecht	Jun 1976
3983535	Herbst et al.	Sep 1976
4020463	Himmel	Apr 1977
4024500	Herbst et al.	May 1977
4028674	Chuang	Jun 1977
4035769	Sternberg et al.	Jul 1977
4040011	Crane et al.	Aug 1977
4040012	Crane et al.	Aug 1977
4055756	Jolivet et al.	Oct 1977
4086567	Crane et al.	Apr 1978
4128829	Herbst et al.	Dec 1978
4143357	Baver et al.	Mar 1979

Non-Patent Literature Citations (9)

Entry
Andrews, "Multidimensional Rotations in Feature Selection", IEEE Trans. on Computers, Sep. 1971, pp. 1045-1051.
Nemcek et al., "Experimental Investigation of Automatic Signature Verification", IEEE Trans. on Systems, Man, and Cybernetics, vol. SMC-4, (1974), pp. 121-126.
Bremermann, "Pattern Recognition, Functionals, and Entropy", IEEE Trans. on Bio-Med. Eng., vol. BME-15, No. 3, pp. 201-207, Jul. 1968.
Meltzer, "Speech Synthesis by Haar Functions with Comparison to a Terminal Analog Device", Ph. D. Dissertation, Ohio State University, pp. 16-30, 1972.
Meltzer et al., "Vowel and Speaker Identification in Natural and Synthetic Speech, JASA, vol. 51, p. 131, Jan. 1972.
Haar; A., "Zur Theorie der Orthogonalen Funktionensysteme", Math. Annalen., vol. 69, pp. 331-371, 1910.
Andrews; H. C., Computer Techniques in Image Processing, Academic Press, pp. 73-103, 1970.
Andrews; H. C. et al., "Kronecker Matrices, Computer Implementation, and Generalized Spectra", JACM, vol. 17, pp. 260-268, Apr. 1970.
Andrews et al., "A Generalized Technique for Spectral Analysis", IEEE Trans. on Computers, vol. C-19, No. 1, pp. 16-25, Jan. 1970.

Identity verification apparatus and method

Information

Patent Number

Date Filed

Date Issued

Inventors

Original Assignees

Examiners

Agents

CPC

US Classifications

Field of Search

US

International Classifications

Abstract

Description

Claims

US Referenced Citations (24)

Non-Patent Literature Citations (9)