Claims
- 1. A computer system for matching fingerprints, comprising:a computer having a user interface, a central processing unit (CPU), a disk storage that contains a plurality of data records representing one or-more fingerprint images and an image capturing subsystem that produces an image of a target fingerprint; a first image stored in the memory, the first image having one or more first points each of the first points located on a respective first curved line; one or more second images stored in the memory, the second image having one or more second points each of the second points located on a respective second curved line; a reference point matcher, executed by the CPU, that determines a correspondence between a first corresponding point in the first image and a second corresponding point in the second image, the first corresponding point being one of the first points and the second corresponding point being one of the second points; and an alignment estimator that estimates alignment between the first image and the second image by determining an angle between a first curved line on which the first corresponding point lies in the first image and a second curved line on which the second corresponding point lies in the second image and the alignment estimator further determining a translation vector between a first vector point on the first curved line and a second vector point on the second curved line.
- 2. A system, as in claim 1, where the first vector point is the first corresponding point and the second vector point is the second corresponding point.
- 3. A system, as in claim 1, where the first curved line and the second curved line are divided into a number of segments, each segment having one or more segment points, a first vector is defined between a first origin and each segment point on the first curved line, a second vector is defined between a second origin and each segment point on the second curved line, a vector angle difference between each corresponding pair of first and second vectors is determined, and the angle is an average of the vector angle differences.
- 4. A system, as in claim 3, where the first origin is the first corresponding point and the second origin is the second corresponding point.
- 5. A system, as in claim 1, where the first and second images are fingerprint images, the curved lines are ridge lines, and the first and second points are minutia.
- 6. A system, as in claim 1, where the first and second curve are similar to one another as determined by an estimation of similarity.
- 7. A system, as in claim 1, where the second image is translated by the translation vector and rotated by the angle so that the first image aligns with the second image.
- 8. A computer system for matching fingerprints, comprising:a computer having a user interface, a central processing unit (CPU), a disk storage that contains a plurality of data records representing one or more fingerprint images and an image capturing subsystem that produces an image of a target fingerprint; a first image stored in the memory, the first image having one or more first points each of the first points located on a respective first curved line; one or more second images stored in the memory, the second image having one or more second points, each of the second points located on a respective second curved line; a reference point matcher, executed by the CPU, that determines a correspondence between a first corresponding point in the first image and a second corresponding point in the second image, the first corresponding point being one of the first points and the second corresponding point being one of the second points; an alignment estimator that estimates alignment between the first image and the second image by determining an angle between a first curved line on which the first corresponding point lies in the first image and a second curved line on which the second corresponding point lies in the second image and the alignment estimator further determining the translation vector between a first vector point on the first curved line and a second vector point on the second curved line, the alignment estimator determining a translation vector and angle between more than one pairs of first and second curved lines.
- 9. A system, as in claim 8, where a vector statistic of the translation vectors and an angle statistic of the angles is used to align the first and second images.
RELATED PATENT APPLICATIONS
This patent claims priority to the provisionally filed patent application number 60/056,677 filed on Aug. 22, 1997.
U.S. patent applications Ser. No. 08/722,714, filed Sep. 30, 1996, now U.S. Pat No. 5,963,656, entitled SYSTEM AND METHOD FOR DETERMINING THE QUALITY OF FINGERPRINT IMAGES to Bolle et al., Ser. No. 08/735,718, filed Oct. 23, 1996, now U.S. Pat No. 5,883,971, entitled SYSTEM AND METHOD FOR DETERMINING IF A FINGERPRINT IMAGE CONTAINS A SMUDGED IMPRESSION to Bolle et al., Ser. No. 08/735,721, filed Oct. 23, 1996, now U.S. Pat No. 6,005,963, entitled SYSTEM AND METHOD FOR DETERMINING IF A FINGERPRINT IMAGE CONTAINS A DRY IMPRESSION to Bolle et al., Ser. No. 08/735,541, filed Oct. 23, 1996, now U.S. Pat No. 6,005,963, entitled SYSTEM AND METHOD FOR DETERMINING IF A FINGERPRINT IMAGE CONTAINS A PARTIAL PRINT to Bolle et al., Ser. No. 06/034,268, filed Dec. 13, 1996, entitled SYSTEM AND METHOD USING MINUTIAE PRUNING FOR FINGERPRINT IMAGE PROCESSING to Bolle et al., Ser. No. 06/032,713, filed Dec. 13, 1996, entitled SYSTEM AND METHOD FOR DETERMINING RIDGE COUNTS IN FINGERPRINT IMAGE PROCESSING to Bolle et al., Ser. No. 08/837,069, filed Apr. 11, 1997, now U.S. Pat. No. 6,111,978, entitled SYSTEM AND METHOD FOR DISTORTION CONTROL IN LIVE-SCAN INKLESS FINGERPRINT IMAGES to Bolle et al., are herein incorporated by reference in their entirety.
US Referenced Citations (3)
Number |
Name |
Date |
Kind |
4771474 |
Takashima et al. |
Sep 1988 |
|
5559901 |
Lobregt |
Sep 1996 |
|
5717777 |
Wong et al. |
Feb 1998 |
|
Foreign Referenced Citations (2)
Number |
Date |
Country |
3-10385 (A) |
Jan 1991 |
JP |
06231266 A |
Aug 1994 |
JP |
Non-Patent Literature Citations (2)
Entry |
Anil Jain, Lin Hong, and Ruud Bolle, “On-line Fingerprint Verification”, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 19, No. 4, pp. 302-314, Apr. 1997.* |
Anil Jain, and Lin Hong, “On-line Fingerprint Verification”,IEEE, Proceedings of ICPR'96, pp. 596-600, Aug. 1996. |
Provisional Applications (1)
|
Number |
Date |
Country |
|
60/056677 |
Aug 1997 |
US |