Determining an alignment estimation between two (fingerprint) images

Claim 2

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.

Claim 3

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.

Claim 4

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.

Claim 5

A system, as in claim 3 , where the first origin is the first corresponding point and the second origin is the second corresponding point.

Claim 6

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.

Claim 7

A system, as in claim 1 , where the first and second curve are similar to one another as determined by an estimation of similarity.

Claim 8

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.

Claim 9

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.

Claim 10

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.

Claim 11

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.