Iris biometric matching system

• US 9,665,772 B2
• Filed: 09/18/2015
• Issued: 05/30/2017
• Est. Priority Date: 12/10/2012
• Status: Active Grant

• Current Assignee: Princeton Identity Inc.
• Original Assignee: SRI International, Inc.
• Inventors: Bergen, James R.
• Primary Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US14/858,715
• Publication Number:
  US 20160012275A1
• Time in Patent Office: 620 Days
• Field of Search: 382115-118, 351206
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/197 Matching; Classification

Abstract

A method and apparatus for biometric iris matching comprising pre-processing an input image capturing one or more eyes to produce one or more rectified iris images, coding the one or more rectified iris images into one or more multiresolution iris codes and matching the one or more multiresolution iris code with a set of stored multiresolution iris codes to determine whether a match exists.

Claims

1. A computer system for biometric iris matching, comprising:

a processor;

memory coupled to the processor, the memory comprising instructions configured to cause the computer system to;

receive at least one input image of an eye;

generate one or more edge maps corresponding to each of the at least one input image;

segment a pupil area in each of the at least one input image;

segment an iris area from a sclera area in each of the at least one input image; and

synthesize an artificial pupil on the at least one input image within the segmented pupil area.

2. The biometric iris matching system of claim 1, configured to construct one or more candidate pupil contours based on the one or more edge map.

3. The biometric iris matching system of claim 2, wherein each edge map contains at least one candidate pupil contour.

4. The biometric iris matching system of claim 1, configured to correct ones of the at least one input image for low-contrast boundaries.

5. The biometric iris matching system of claim 4, configured to correct ones of the at least on einput image for iris boundaries.

6. The biometric iris matching system of claim 1, configured to normalize iris diameters in ones of the at least one input image using a range estimate derived from an autofocus setting of a camera taking the at least one input image.

7. The biometric iris matching system of claim 1, configured to produce one or more rectified iris images.

8. The biometric iris matching system of claim 7, configured to transform the rectified iris images into transformed iris images.

9. The biometric iris matching system of claim 8, wherein the transformed iris images are invariant coordinate system image representations of the rectified iris images.

10. The biometric iris matching system of claim 9, configured to mask off specular reflections and unstable regions in the transformed iris images to produce masked converted iris images.

11. The biometric iris matching system of claim 10, configured to subsample the masked transformed iris images into a plurality of filtered images that range from high frequency bands to low frequency bands.

12. A computer system for biometric iris matching, comprising:

a processor; and

memory comprising instructions configured to cause the computer system to;

receive at least one input image of an eye;

estimate an angle of tilt of the eye in the at least one input image with respect to a camera that captured the image; and

correct corneal distortion based on the estimated angle of tilt.

13. The iris biometric matching system of claim 12, configured to correct corneal distortion by aligning an iris contour and a pupil contour of the eye into concentric circles.

14. The biometric iris matching system of claim 12, configured to correct for perspective distortion based on the estimated angle of tilt.

15. The biometric iris matching system of claim 12, wherein the estimate of the angle of tilt is based at least in part on a location of a reflection in the cornea of the eye in the at least one input image with respect to the camera orientation.

16. The biometric iris matching system of claim 12, configured to stretch the input image in the estimated direction of tilt.

17. The biometric iris matching system of claim 12, configured to apply an affine or projective transformation to the at least one input image.

18. A method for biometric iris matching, implemented on a computer system, the method comprising:

receiving at least one input image of an eye;

segmenting a pupil area in an eye detected in at least one input image;

selecting a pupil contour based on one or more of a best fitting circle and a best inscribed circle; and

segmenting an iris area from a sclera area in each of the one or more eyes in the input image.

19. The method for biometric iris matching of claim 18, comprising:

constructing one or more candidate pupil contours based on one or more edge maps, wherein each edge map comprises at least one candidate pupil contour; and

determining a best matching candidate pupil contour for each eye in the input image.

20. The method for biometric iris matching of claim 19, comprising generating one or more edge maps corresponding to each eye in the input image.