Patent Application
20050025344
1. Field of the Invention
The present invention is generally related to biometric imaging systems. More particularly, the present invention is related to the reliable obtainment of quality biometric print images.
2. Background Art
Biometrics is a science involving the analysis of biological characteristics. Print capture and recognition is an important biometric technology. Law enforcement, banking, voting, and other industries increasingly rely upon prints as a biometric to store, recognize or verify identity. See, e.g., Gary Roethenbaugh, “Biometrics Explained,” International Computer Security Association, Inc., pp. 1-34 (1998), which is incorporated by reference herein in its entirety. Generally, a biometric is a measurable, physical characteristic or personal behavior trait used to recognize the identity, or verify the claimed identity, of a person who has a biometric reference template (e.g., data that represents a biometric measurement) on file.
There are a number of different types of biometric imaging systems. For example, one type of biometric imaging system is a print scanner (also called a live scanner). Print scanners often serve as input devices to an Automatic Fingerprint Identification System (AFIS). Automatic Fingerprint Identification Systems can be used for law enforcement purposes to collect print images from criminal suspects when they are arrested.
One type of print scanner is a ten-print scanner. Typically, ten-print scanners require each finger to be imaged using a roll print technique. A flat print technique or a slap print technique may also be used. Unfortunately, it is sometimes difficult to obtain quality prints because of the scanner timing or the awkward placement of the fingers. For example, an operator of an AFIS input device may have to reset the device and/or rescan every time a user does not place his or her fingers on a scanner platen correctly. Or, as an alternative example, the operator may have to reset the device and/or rescan every time a user does not get his or her fingers in place before the scanner captures an image. Poor print quality or incorrect placement can cause a set of captured prints to be rejected by an AFIS. The result of having to deal with such difficulties is that the process of obtaining prints, such as during an arrest or background check, becomes relatively complex and time-consuming.
Currently, biometric imaging systems lack the ability to reliably capture quality biometric print images. What is needed is a system and method of efficiently capturing biometric print images of good quality and integrity.
Embodiments of the present invention provide a biometric imaging system and method that can reliably process and capture quality print images while ensuring data and print image integrity. The system and method can be used to capture print impressions as a single image and segment the single image to create separate images for further processing.
Embodiments of the present invention provide a method including the steps of initiating camera operation within a scanner, scanning a biometric object to obtain a scanned print image, processing the scanned image, determining the print quality of individual print images in the scanned image, detecting prints in the scanned image, and determining whether the scanned image is ready for capture based on an expected number of prints detected and the quality of those print images. The method includes capturing the scanned image, processing the captured image, and forwarding the captured image to a computer. The method further includes allowing an operator to annotate quality issues regarding the captured image, such as information about individual print images that are missing or of unacceptable quality. The method also includes timing out the scanner when no print images are detected and a predetermined scanner timeout period has expired.
Embodiments of the present invention provide a method including filtering a scanned image, binarizing the filtered image, detecting print area based on the binarized image, detecting print contrast based on the detected print area and the scanned image, detecting print shape based on the binarized image, and separating the print image into individual print images based on the print area, contrast, and shape detected. The method also includes determining print image quality of each individual print image based on minutiae data extracted from the individual print images, such as pattern detail.
Embodiments of the present invention provide a method including classifying each individual print image based on a predetermined quality threshold and indicating a quality classification of the individual print images to an operator.
Embodiments of the present invention provide a method including the use of a predetermined capture delay time period, quality time period, and scanner timeout period, which contribute to the effectiveness of the method.
Embodiments of the present invention are directed to a biometric print imaging system for reliably processing and capturing print images. The system includes means of providing the method steps in the aforementioned method embodiments.
Embodiments of the present invention are directed to a biometric print image scanner system that reliably captures print images. The system includes a scanner that scans print images of biometric objects. The scanner includes a print capture manager that determines when a scanned print image is ready for capture. The system also includes a computer that stores and displays data regarding the captured print images. The computer also allows an operator to input annotation regarding the captured print images. The system also includes a communication link between the computer and the scanner that allows the transfer of data regarding the captured print images.
Embodiments of the present invention include a scanner with a sensor that detects print images, an output device that displays to an operator information regarding the scanned print images, and a controller that controls interoperation of the sensor, the print capture manager, and the output device. The sensor includes a platen that receives biometric objects, such as fingers or thumbs, and a camera that scans print images of the biometric objects. The output device includes individual quality indicators for individual print images. The individual quality indicators are areas of a liquid crystal display (LCD) highlighted by symbols, shades, or colors that represent a quality classification of each individual print image.
Embodiments of the present invention include a computer that includes a memory that stores data regarding captured print images. The computer also includes an operator interface that displays to an operator the captured print image data and allows an operator to input annotation regarding the captured print images. The operator interface includes a monitor on which an operator can view captured print image information and an input device from which an operator can input annotation.
Further embodiments, features, and advantages of the present invention, as well as the structure and operation of the various embodiments of the present invention, are described in detail below with reference to the accompanying drawings.
The accompanying drawings, which are incorporated herein and form part of the specification, illustrate the present invention and, together with the description, further serve to explain the principles of the invention and to enable a person skilled in the pertinent art(s) to make and use the invention.
The features and advantages of the present invention will become more apparent from the detailed description set forth below when taken in conjunction with the drawings in which like reference characters identify corresponding elements throughout. In the drawings, like reference numbers generally indicate identical, functionally similar, and/or structurally similar elements. The drawings in which an element first appears is indicated by the leftmost digit(s) in the corresponding reference number.
While the present invention is described herein with reference to illustrative embodiments for particular applications, it should be understood that the invention is not limited thereto. Those skilled in the art(s) with access to the teachings provided herein will recognize additional modifications, applications, and embodiments within the scope thereof and additional fields in which the present invention would be of significant utility.
Sections
To more clearly delineate the present invention, an effort is made throughout the specification to adhere to the following term definitions consistently.
The term “finger” refers to any digit on a hand including, but not limited to, a thumb, an index finger, middle finger, ring finger, or a pinky finger.
The term “print” can be any type of print including, but not limited to, a print of all or part of one or more fingers, palms, toes, foot, hand, etc. A print can also be a rolled print, a flat print, or a slap print.
The term “print image” refers to any of the various types of image data representing the print, which may include, but is not limited to, grey scale data, binary data, or any other type of raw or processed image data.
The term “biometric data” or “biometric information” throughout the specification can be any data representative of a biometric, a digital or other image of a biometric (e.g., a bitmap or other file), extracted digital or other information relating to the biometric (e.g., a template based on minutiae detail), etc. The data may refer to print boundaries, contrast, or ridge patterns, for example.
The term “minutiae” includes unique and measurable physical characteristics of a print. For fingerprints, minutiae include the starting and ending point of ridges and ridge junctions among features.
The term “scan” refers to the taking of any type of print image by a print scanner. A scan can include, but is not limited to, a scan of a finger, a finger roll, a flat finger, slap print of four fingers, thumb print, palm print, or a combination of fingers, such as, sets of fingers and/or thumbs from one or more hands or one or more palms disposed on a platen.
In a scan, one or more fingers or palms from either a left hand or a right hand or both hands are placed on a platen of a scanner. Different types of print images are detected depending upon a particular application. For example, a flat print consists of a fingerprint image of a digit (finger or thumb) pressed flat against the platen. A roll print consists of an image of a digit (finger or thumb) made while the digit (finger or thumb) is rolled from one side of the digit to another side of the digit over the surface of the platen. A slap print consists of an image of four flat fingers pressed flat against the platen. A platen can be movable or stationary depending upon the particular type of scanner and the type of print being captured by the scanner.
The terms “biometric imaging system,” “scanner,” “fingerprint scanner,” and “print scanner” are used interchangeably, and refer to any type of scanner which can obtain an image of all or part of one or more fingers, palms, toes, foot, hand, etc. in a live scan. The obtained images can be combined in any format including, but not limited to, a Federal Bureau of Investigation (FBI), state, or international ten-print format.
The Biometric Imaging System
Embodiments of the present invention provide a biometric imaging system and method. Although ten-print capture and four finger slap capture are the preferred system and method described throughout the specification and/or claims, it is to be appreciated that any available number of fingers and/or thumbs are also contemplated within the scope of the present invention. Thus, even when the above terminology is used, it can include less fingers and/or thumbs. In addition, it is to be appreciated that other biometric objects having prints are also contemplated within the scope of the present invention, including palms, hand, toes, foot, etc.
The biometric imaging system can provide a simplified way to reliably capture biometric image prints. For example, fingerprints can be captured by allowing four finger slap impressions to be captured in a single image. A simultaneous impression of the four fingers from one hand captured as a single image can then be segmented to create up to four separate images. After the fingerprints from the fingers from both hands are captured, thumb prints from both hands can be captured simultaneously. Each individual extracted image can then be placed within the corresponding finger and/or thumb print box on a fingerprint card to save for future identification or verification purposes. Examples of such processes for print capture and separation are further described in U.S. patent application Ser. No. 10/345,420 and U.S. patent application Ser. No. 10/345,366, which are incorporated by reference herein in their entireties.
Proper sequencing of the placement of biometric objects (e.g., finger and/or thumb prints) can be performed using software analysis and/or physical properties of a platen. The platen may also include a finger guide to help physically divide digits. This process is further described in U.S. patent application Ser. No. 10/345,420 and U.S. patent application Ser. No. 10/345,366, which are incorporated by reference herein in their entireties.
Biometric print images can be presented on a screen, such as a monitor coupled to a personal computer, to provide real time quality checks and assistance with correction. This is further described with reference to
Computer 102 may be any commercial off-the-shelf computer. For example, computer 102 may be a personal computer (PC). An example implementation of computer 102 is described in U.S. patent application Ser. No. 10/345,420 and U.S. patent application Ser. No. 10/345,366, which are incorporated by reference herein in their entireties. After reading this description, it will be apparent to a person skilled in the relevant art how to implement the invention using other computer systems and/or computer architectures.
Computer 102 includes a memory 110. Memory 110 is preferably random access memory (RAM), however other types of memory may be used, such as a hard disk drive, or removable storage units such as a floppy disk, a magnetic tape, an optical disk, etc. Removable storage units are read by and written to by removable storage drives. As will be appreciated, a hard disk drive and a removable storage unit may each include a computer usable storage medium having stored therein computer software and/or data.
Referring to
In an embodiment of the present invention, operator interface 108 includes a monitor (not shown) and input device (e.g., a keyboard and/or mouse) (not shown). For example, the monitor is used to provide real-time feedback to an operator with regard to current captured biometric print images. In addition, the input device is used by the operator to input annotation with regard to captured biometric print images.
In an embodiment of the present invention, scanner 104 includes a sensor 114, a controller 116, and an output device 118. Controller 116 includes print capture manager 117. Scanner 104 illuminates an area of a platen (not shown) for receiving one or more fingers. In an embodiment, sensor 114 is a camera such as a digital camera. Sensor 114 detects print images of prints placed on the platen. Controller 116 controls the interoperation of sensor 114, print capture manager 117, and output device 118. Print capture manager 117 captures print images in an embodiment of the present invention as described further below with respect to
Control functionality described above, including all or part of the functionality of print capture manager 117, can be carried out by a scanner, such as a ten-print scanner, a computer coupled to the scanner, or distributed between both the scanner and the computer. Embodiments of the system have been described above with regard to a camera, including but not limited to a digital camera. This is not intended to limit the present invention because any type of sensor, detector, or camera can be used to scan and capture a print image as is known in the art.
Real-Time Feedback Quality Indicators
In one embodiment of the present invention, output device 118 indicates the quality of a biometric print image. This feedback is provided in real-time by the system with every image scanned. For example, output device 118 could include one or more quality indicators, perhaps with each quality indicator associated with a specific finger of a four-slap fingerprint image. In one embodiment of the invention, output device 118 includes one or more indicators comprising light-emitting diodes (LEDs). In another embodiment, the indicators are multi-color LEDs. In that embodiment, a red LED may indicate poor quality, a green LED may indicate acceptable quality, and an amber LED may indicate possibly acceptable quality. In another embodiment, the indicators are bar graph LED indicators, wherein the level of the bar indicates quality acceptance. In still further embodiments, the indicators are any electrical, mechanical, or audio device or signal known to alert a user of a condition, as would be known to one skilled in the art. In one embodiment, different symbols are used on a liquid crystal display (LCD) to indicate quality level, as depicted in
Quality indications can also be displayed at a separate display on the biometric imaging system. For example, an external computer 102 can output a variety of displays on a monitor indicating quality of print images.
Method of Processing and Capturing Print Images
If in step 338, print capture manager 117 detects no prints, and has not detected any prints during a predetermined timeout period in step 340, then print capture manager 117 issues a control signal timeout to scanner 104 in step 342, and routine 300 ends at step 358. The purpose of the predetermined timeout period is to time out scanner 104 if it is determined that no prints were detected during that amount of time. For example, if an operator initiates imaging system 100, but no one places fingers on the platen for the predetermined timeout period, then scanner 104 times out. Alternatively, if a user places fingers on the platen for scanning, but subsequently removes them, and they remain removed for the predetermined timeout period, scanner 104 times out. In an embodiment of the present invention, the predetermined timeout period is sixty seconds. However, the predetermined timeout period is adjustable. A scanner timeout typically entails the stoppage of camera operation. If no prints are detected in step 338, and the predetermined timeout period in step 340 has not expired, then the routine returns to step 332 to scan the biometric object to obtain a subsequent print image.
In an embodiment of the present invention, print capture manager 117 expects four prints for a four finger slap image or expects two prints for an image of the thumbs. If prints are detected in step 338, then print capture manager 117 determines whether the scanned image is ready for capture based on the expected number of prints and the quality of the scanned print images. If not all expected prints are present within the scanned print image, or if not all of the expected prints are of good quality, then the routine continues at step 348.
In step 348, print capture manager 117 determines whether a predetermined quality time period has expired. In an embodiment of the present invention, the predetermined quality time period is five seconds. However, the predetermined quality time period is adjustable. For example, in an embodiment of the invention, if not all expected prints are present within the scanned print image, or if not all of the expected prints are of good quality, then the system determines whether it has been attempting to capture this set of prints for a predetermined quality time period of five seconds. If the predetermined quality time period has not expired in step 348, then the routine returns to step 332 to scan the biometric object to obtain a subsequent print image. If, on the other hand, in step 348, imaging system 100 determines that the predetermined quality time period has expired, the routine continues at step 350.
In step 350, the latest scanned print image is captured. In step 352, the captured image is processed. The processing step 352 is herein further described later in reference to
Referring again to step 344, if all expected prints are present within the scanned image and are all of good quality, then print capture manager 117 determines at step 346 whether the prints remained in this state for a predetermined capture delay time period. In an embodiment of the present invention, the predetermined capture delay time period is one half second. However, the predetermined capture delay time period is adjustable. If in step 346 the prints remained in this state for a predetermined capture delay time period, then the routine continues at step 350. In step 350, the latest scanned image is captured. In step 352, the captured image is processed. The processing step 352 is herein further described later in reference to
Referring again to step 346, if the expected prints do not remain present or if they do not all remain in good quality for the predetermined capture delay time period, then the routine continues at step 348. Step 348 is described earlier herein.
In step 362, a binarization process is performed. The binarization process removes all of the grey areas and replace them with either black or white pixels based on a black and white threshold point. In one embodiment, the binarization process begins by taking an average grey scale value of the filtered image. In this instance, the average grey scale value is the black and white threshold point. In this embodiment, all of the pixel values above the average value are replaced with white pixels and all the pixel values equal to and below the average value are replaced with black pixels. The resulting image is comprised of all black and white pixels that define a print area, contrast, and shape.
In step 364, a print area is detected. Usually, the black areas of the image are concentrated around the prints. Thus, the detection step detects the areas concentrated by black pixels. In step 366, the print contrast is detected. Print contrast is further evidence of print area. For example, if the contrast is found to be low, that area of low contrast may not even be associated with the print image. In step 368, print shapes are detected. For example, fingerprint shapes can be oval-like shapes. In the print shape detection step, the areas concentrated by black pixels that are comprised of oval-like shapes are detected. In step 370, the print image is separated into individual print images based on the print area, contrast, and shape detected. Step 372 ends the routine for processing the scanned image and allows the calling routine to continue where it left off.
As described earlier with reference to step 354 in
While specific embodiments of the present invention have been described above, it should be understood that they have been presented by way of example only, and not limitation. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined in the appended claims. Thus, the breadth and scope of the present invention should not be limited by any of the above-described exemplary embodiments, but should be defined only in accordance with the following claims and their equivalents.
The present application is related to U.S. Provisional Patent Application No. 60/348,678, filed on Jan. 17, 2002, which is incorporated by reference herein in its entirety. The present application is related to U.S. patent application Ser. No. 10/345,420 and U.S. patent application Ser. No. 10/345,366, both filed on Jan. 16, 2003, which are incorporated by reference herein in their entireties.
