IP Library Granted Patent US 9,946,917
Granted Patent B2
US 9,946,917 · App. 15/086,906 · Granted Apr 17, 2018

Efficient determination of biometric attribute for fast rejection of enrolled templates and other applications

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,946,917
App. No.
15/086,906
Granted
Apr 17, 2018
Kind
B2
Abstract

A biometric input system includes: a biometric sensor, configured to generate a biometric image comprising features of an input biometric object; and a processing system, configured to receive the biometric image, generate a feature map from the biometric image, perform a distance transform on the feature map, and determine an attribute of the biometric image from the distance transform. The processing system is further configured to compare the determined attribute of the biometric image with corresponding attributes of enrolled biometric images, and, based on the comparison, to eliminate enrolled biometric images from a matching process for the biometric image, wherein the matching process is performed after the elimination and comprises comparison of the biometric image to remaining enrolled biometric images based on one or more attributes of the biometric image other than the determined attribute.

Claims (48)

1. A biometric input system, comprising:

a biometric sensor, configured to generate a biometric image comprising features of an input biometric object; and

a processing system, configured to receive the biometric image, generate a feature map from the biometric image, perform a distance transform on the feature map, and determine an attribute of the biometric image from the distance transform;

wherein the processing system is further configured to compare the determined attribute of the biometric image with corresponding attributes of enrolled biometric images, and, based on the comparison, to eliminate enrolled biometric images from a matching process for the biometric image, wherein the matching process is performed after the elimination and comprises comparison of the biometric image to remaining enrolled biometric images based on one or more attributes of the biometric image other than the determined attribute.

2. The system according to claim 1 , wherein the input biometric object is a fingerprint, and the feature map is a skeletonized ridge representation of the fingerprint.

3. The system according to claim 2 , wherein generating the feature map from the biometric image comprises:

generating a binary image from the received biometric image; and

thinning each ridge of the binary image to a single pixel width.

4. The system according to claim 2 , wherein the performed distance transform indicates a distance-to-nearest-ridge for each pixel of the feature map.

5. The system according to claim 4 , wherein determining the attribute of the biometric image from the distance transform further comprises:

identifying local maxima based on the performed distance transform; and

determining the attribute of the biometric image based on the identified local maxima.

6. The system according to claim 5 , wherein the determined attribute comprises a median or mean half ridge spacing value.

7. The system according to claim 5 , wherein the determined attribute comprises a distribution of half ridge spacing values.

8. The system according to claim 1 , wherein the processing system is further configured to determine an age, gender, or ethnicity corresponding to the input biometric object based on the determined attribute.

9. A biometric input method, comprising:

obtaining, by a processing system, a biometric image of an input biometric object;

generating, by the processing system, a skeletonized ridge representation of the input biometric object based on the obtained biometric image;

performing, by the processing system, a distance transform on the skeletonized ridge representation to determine a distance-to-nearest-ridge for each pixel of the skeletonized ridge representation;

identifying local maxima based on the performed distance transform; and

determining an attribute of the biometric image based on the performed distance transform and the identified local maxima.

10. The method according to claim 9 , further comprising:

comparing, by the processing system, the determined attribute of the biometric image with corresponding attributes of enrolled biometric images;

eliminating, by the processing system, based on the comparing, enrolled biometric images from a matching process for the biometric image; and

performing, by the processing system, the matching process for the biometric image, wherein performing the matching process comprises comparing one or more attributes of the biometric image other than the determined attribute to enrolled biometric images remaining after the elimination.

11. The method according to claim 9 , wherein the obtained biometric image is a full or partial view of a fingerprint, and wherein the method further comprises:

identifying one or more fingers corresponding to the obtained biometric image based on the determined attribute.

12. The method according to claim 9 , wherein the obtained biometric image is a partial view of a fingerprint, and wherein the method further comprises:

determining a localization of the partial view of the fingerprint within the fingerprint based on the determined attribute.

13. The method according to claim 9 , further comprising:

determining an age, gender, or ethnicity corresponding to the input biometric object based on the determined attribute.

14. The method according to claim 9 , wherein the determined attribute is based on a ridge spacing-related value or a distribution of ridge spacing-related values.

15. A non-transitory, computer-readable medium having processor-executable instructions stored thereon for biometric input, the processor-executable instructions, when executed, facilitating performance of the following:

generating a skeletonized ridge representation of an input biometric image corresponding to an input biometric object;

performing a distance transform on the skeletonized ridge representation to determine a distance-to-nearest-ridge for each pixel of the skeletonized ridge representation;

identifying local maxima based on the performed distance transform; and

determining an attribute of the biometric image based on the performed distance transform and the identified local maxima.

16. The non-transitory, computer-readable medium according to claim 15 , wherein the processor-executable instructions, when executed, further facilitate:

comparing the determined attribute of the biometric image with corresponding attributes of enrolled biometric images;

eliminating, based on the comparing, enrolled biometric images from a matching process for the biometric image; and

performing the matching process for the biometric image, wherein performing the matching process comprises comparing one or more attributes of the biometric image other than the determined attribute to enrolled biometric images remaining after the elimination.

17. The non-transitory, computer-readable medium according to claim 15 , wherein the obtained biometric image is a full or partial view of a fingerprint, and wherein the processor-executable instructions, when executed, further facilitate:

identifying one or more fingers corresponding to the obtained biometric image based on the determined attribute.

18. The non-transitory, computer-readable medium according to claim 15 , wherein the obtained biometric image is a partial view of a fingerprint, and wherein the processor-executable instructions, when executed, further facilitate:

determining a localization of the partial view of the fingerprint within the fingerprint based on the determined attribute.

19. The non-transitory, computer-readable medium according to claim 15 , further comprising:

determining an age, gender, or ethnicity corresponding to the input biometric object based on the determined attribute.

20. The non-transitory, computer-readable medium according to claim 15 , wherein the determined attribute is based on a ridge spacing-related value or a distribution of ridge spacing-related values.

Assignments (3)
CORRECTIVE ASSIGNMENT TO CORRECT THE CORRECT THE SPELLING OF THE ASSIGNOR NAME PREVIOUSLY RECORDED AT REEL: 051316 FRAME: 0777. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Mar 18, 2020
From: SYNAPTICS INCORPORATED
To: WELLS FARGO BANK, NATIONAL ASSOCIATION
Reel/Frame 052186/0756 →
SECURITY INTEREST Recorded Dec 16, 2019
From: SYNAPTICS INCORPROATED
To: WELLS FARGO BANK, NATIONAL ASSOCIATION
Reel/Frame 051316/0777 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 31, 2016
From: TIEU, KINH; MACKEY, BOB LEE
To: SYNAPTICS INCORPORATED
Reel/Frame 038166/0593 →