Invariant radial iris segmentation

• US 20070211924A1
• Filed: 03/10/2006
• Published: 09/13/2007
• Est. Priority Date: 03/03/2006
• Status: Active Grant

• Current Assignee: Gentex Corporation
• Original Assignee: Honeywell International Inc.
• Inventors: Hamza, Rida
• Granted Patent: US 8,442,276 B2
• Time in Patent Office: Days
• US Class Current: 382/117
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

A method and computer product are presented for identifying a subject by biometric analysis of an eye. First, an image of the iris of a subject to be identified is acquired. Texture enhancements may be done to the image as desired, but are not necessary. Next, the iris image is radially segmented into a selected number of radial segments, for example 200 segments, each segment representing 1.8° of the iris scan. After segmenting, each radial segment is analyzed, and the peaks and valleys of color intensity are detected in the iris radial segment. These detected peaks and valleys are mathematically transformed into a data set used to construct a template. The template represents the subject'"'"'s scanned and analyzed iris, being constructed of each transformed data set from each of the radial segments. After construction, this template may be stored in a database, or used for matching purposes if the subject is already registered in the database.

Claims

1. A method of identifying a subject by biometric analysis of the iris of an eye, the method comprising the steps of:

(1) acquiring an image of an iris of the subject;

(2) radially segmenting the iris image into a plurality of radial segments;

(3) for each radial segment, determining data for a predetermined one dimensional feature within said segment relative to a reference value of said feature within said image; and

(4) constructing a template for said subject comprising said data set for each of said radial segments.

20. The method of claim 1 wherein step (1) comprises preprocessing said image by performing texture enhancement on said image and dropping out parts of said image that obscure said iris.

2. The method of claim wherein step (2) comprises the steps of:

(2.1) determining a center of a pupil of said subject; and

(2.2) determining a pupil-iris border in said image; and

(2.3) radially segmenting said iris into a plurality of radial segments of equal angular size.

3. The method of claim 2 wherein said feature is peaks of color intensity and wherein said data comprises a distance from said pupil-iris border of a one of said peaks that is the farthest from said pupil-iris border within a predetermined distance of said pupil-iris border.

4. The method of claim 2, wherein said one-dimensional data comprises a distance from said pupil-iris border of a largest one of said peaks in said radial segment.

5. The method of claim 2 wherein said feature comprises peaks of color intensity and wherein said one dimensional data comprises the relative magnitudes of said peaks and their relative locations along a direction radially outward from said center of said pupil.

6. The method of claim 5 wherein said relative magnitudes are determined by interpolating data across a width of each said radial segment.

7. The method of claim 5 wherein said magnitudes are determined by averaging data across a width of each radial segment.

8. The method of claim 5 wherein said reference value is a value of a one of said peaks corresponding to color intensity at said pupil-iris border.

9. The method of claim 8 wherein step (3) includes the step of removing a decomposition curve from said detected peaks and valleys.

10. The method of claim 5 further comprising the step of:

(5) encoding said data into a data set.

11. The method of claim 10 wherein, in step (5), a first predetermined number of bits are used to represent data of each peak in said radial segment and each said data set comprises a second predetermined number of bits corresponding to a predetermined number of peaks that can be encoded in said data set, and:

if the number of peaks in said radial segment is less than said predetermined number of peaks that can be encoded, filling said data set with bits indicating an unknown peak; and

if the number of peaks in said radial segment is greater than said predetermined number of peaks that can be encoded, encoding a subset of said peaks in said radial segment.

12. The method of claim 11 wherein said subset of peaks comprises said peaks in said radial segment that are closest to a pupil of said subject.

13. The method of claim 11 wherein said subset of peaks comprises the largest peaks detected in said radial segment.

14. The method of claim 10 further comprising the step of:

(6) comparing said subject'"'"'s template to at least one stored template to determine if said subject'"'"'s template matches said at least one stored template.

15. The method of claim 14 wherein step (6) further comprises the step of weighting each encoded data set such that bits corresponding to peaks closer to said subject'"'"'s pupil are more heavily weighted than bits farther from said subject'"'"'s pupil.

16. The method of claim 10 wherein step (6) comprises:

determining an order of said peaks in said radial segment;

assigning a first value to each peak having a magnitude that is greater than a preceding peak in said order;

assigning a second value to each peak having a magnitude that is lesser than a preceding peak in said order; and

placing said values in said data set in accordance with said order.

17. The method of claim 16, wherein said reference value is a value of a one of said peaks corresponding to color intensity at said pupil-iris border and wherein said peaks are ordered in accordance with their distance from the subject'"'"'s pupil.

18. The method of claim 10, wherein said encoding comprises encoding each peak in said dataset as a two bit sequence wherein a first two bit sequence represents a peak with a high magnitude, a second two bit sequence represents a peak with a low magnitude, and third and fourth two bit sequences both represent a peak with a medium magnitude.

19. The method of claim 18, wherein said encoding is performed with one bit error tolerance.

21. A computer program product embodied on a computer readable medium for identifying a subject by biometric analysis of the iris of an eye, the product comprising:

first computer executable instructions for acquiring an image of an iris of the subject;

second computer executable instructions for radially segmenting the iris image into a plurality of radial segments;

third computer executable instructions for determining data for a predetermined one dimensional feature within said segment relative to a reference value of said feature within said image; and

fourth computer executable instructions for constructing and storing a template for said subject comprising said data set for each of said radial segments.

22. The product of claim 21 wherein said second computer executable instructions comprises:

instructions for determining a center of a pupil of said subject; and

instructions for determining a pupil-iris border in said image; and

instructions for radially segmenting said iris into a plurality of radial segments of equal angular size.

23. The product of claim 22 wherein said feature is peaks of color intensity and wherein said data comprises a distance from said pupil-iris border of a one of said peaks that is the farthest from said pupil-iris border within a predetermined distance of said pupil-iris border.

24. The product of claim 22 wherein said one-dimensional data comprises a distance from said pupil-iris border of a largest one of said peaks in said radial segment.

25. The product of claim 22 wherein said feature comprises peaks of color intensity and wherein said one dimensional data comprises the relative magnitudes of said peaks and their relative locations along a direction radially outward from said center of said pupil.

26. The product of claim 25 wherein said relative magnitudes are determined by interpolating data across a width of each said radial segment.

27. The product of claim 25 wherein said magnitudes are determined by averaging data across a width of each radial segment.

28. The method of claim 25 wherein said reference value is a value of a one of said peaks corresponding to color intensity at said pupil-iris border.

29. The product of claim 28 wherein said third computer executable instructions include instructions for removing a decomposition curve from said detected peaks and valleys.

30. The product of claim 29 further comprising:

fifth computer executable instructions include instructions for encoding said data sets.

31. The product of claim 30 wherein, in said fifth computer executable instructions, a first predetermined number of bits are used to represent data of each peak in said radial segment and each said data set comprises a second predetermined number of bits corresponding to a predetermined number of peaks that can be encoded in said data set, and:

if the number of peaks in said radial segment is less than said predetermined number of peaks that can be encoded, filling said data set with bits indicating an unknown peak; and

if the number of peaks in said radial segment is greater than said predetermined number of peaks that can be encoded, encoding a subset of said peaks in said radial segment.

32. The product of claim 31 wherein said subset of peaks comprises the peaks in said radial segment that are closest to a pupil of said subject.

33. The product of claim 31 wherein said subset of peaks comprises the largest peaks detected in said radial segment.

34. The product of claim 31 further comprising:

sixth computer executable instructions for comparing said subject'"'"'s template to at least one stored template to determine if said subject'"'"'s template matches said at least one stored template.

35. The product of claim 34 wherein said sixth computer executable instructions further comprise instructions for weighting each encoded data set such that bits corresponding to peaks closer to said subject'"'"'s pupil are more heavily weighted than bits farther from said subject'"'"'s pupil.

36. The product of claim 31 wherein said sixth computer executable instructions comprises:

instructions for determining an order of said peaks in said radial segment;

instructions for assigning a first value to each peak having a magnitude that is greater than a preceding peak in said order;

instructions for assigning a second value to each peak having a magnitude that is lesser than a preceding peak in said order; and

instructions for placing said values in said data set in accordance with said order.

37. The product of claim 36, wherein said reference value is a value of a one of said peaks corresponding to color intensity at said pupil-iris border and wherein said peaks are ordered in accordance with their distance from the subject'"'"'s pupil.