A DISTANCE IRIS RECOGNITION

• US 20070036397A1
• Filed: 01/25/2006
• Published: 02/15/2007
• Est. Priority Date: 01/26/2005
• Status: Active Grant

• Current Assignee: Gentex Corporation
• Original Assignee: Honeywell International Inc.
• Inventors: Hamza, Rida
• Granted Patent: US 7,593,550 B2
• Time in Patent Office: Days
• US Class Current: 382/117
• CPC Class Codes: G06V 40/18 Eye characteristics, e.g. of the iris
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

A system for one dimensional segmentation of an iris of an eye into a map of the iris and classification of the map into unaffected areas and affected areas. Also, the system may provide for regular shape fitting of the areas for normalization and identifying the unaffected areas as symmetric segments. Further, the system may assign weights to the unaffected areas and the affected areas of the map of the iris and an enrolled map of an iris and their corresponding bins for matching purposes.

Claims

1. A method comprising:

acquiring an image of an eye;

estimating a center of the pupil;

identifying a border of the pupil;

adjusting the center of the pupil; and

segmenting an iris from the border of the pupil to at least an outside border of the iris.

2. The method of claim 1, further comprising estimating a shape of the iris.

3. The method of claim 2, further comprising adjusting an eye image orientation using perspective projection based on availability of face orientation angles.

4. The method of claim 2, wherein:

the border of the pupil is an inside border of the iris; and

the shape of the iris is estimated as a regular shape while extracting the irregular actual shape of the inside border and the outside border of the iris.

5. The method of claim 4, further comprising delineating symmetric segments from a curvature perspective opposite of each other encompassing the pupil border and the outside border of the iris.

6. The method of claim 5, wherein the identifying the border of the pupil is a snake delineation of the border of the pupil and the outside border of the iris.

7. The method of claim 6, wherein the snake delineation is performed with one dimensional segmentation.

8. The method of claim 7, wherein the one dimensional segmentation is performed in a polar domain originating at about the center of the pupil.

9. The method of claim 8, wherein:

the border of the pupil and the outside border of the iris are deployed in an analysis as irregular curves without further approximation to regular shapes; and

the irregular shapes are normalized in the polar map.

10. The method of claim 9, wherein the shape is estimated as an elliptic shape.

11. The method of claim 8, further comprising classifying the shape into unaffected regions and affected regions.

12. The method of claim 11, further comprising:

normalizing the unaffected regions and the affected regions; and

wherein scaling for the normalizing of the affected regions varies based on obscuration by extraneous objects of the affected regions.

13. The method of claim 12, further comprising identifying symmetric segments of the unaffected regions.

14. The method of claim 13, wherein the affected segments comprise obscured affected regions and non-obscured affected regions.

15. The method of claim 13, further comprising clustering to divide the affected regions into obscured affected regions and non-obscured affected regions.

16. The method of claim 15, wherein the clustering is texture clustering using mixture modeling.

17. The method of claim 15, further comprising masking the obscured affected regions.

18. The method of claim 14, wherein:

the non-obscured affected regions are part of a fitting mechanism; and

an irregular actual shape is estimated from unaffected regions and non-obscured affected regions as an elliptic or regular shape.

19. The method of claim 14, wherein an irregular actual shape is estimated from an unaffected regions and non-obscured affected regions as an elliptic regular shape with a least square fitting approach applied to an elliptic quadratic curve.

20. The method of claim 14, wherein an irregular actual shape is estimated from an unaffected regions and non-obscured affected regions as an elliptic regular shape with elliptic fitting using overlapping variable circles.

21. The method of claim 14, wherein an irregular actual shape is estimated from an unaffected regions and non-obscured affected regions as an elliptic regular shape with a scaling mechanism to transfer an elliptic fitting approach into a circular fitting approach, and scaling the estimated circle back to elliptic regular shape.

22. The method of claim 14, further comprising assigning weighting to the unaffected regions and the affected regions.

23. The method of claim 22, encoding the affected regions and the unaffected regions into symmetric bins and asymmetric bins, respectively.

24. The method of claim 23, further comprising matching the symmetric bins and asymmetric bins with symmetric bins and asymmetric bins, not necessarily respectively, of other irises.

25. The method of claim 24, wherein a weighting accorded a match of the symmetric bins is significantly greater than a weighting accorded a match of the asymmetric bins.

26. The method of claim 25, wherein a weighting accorded a match of the symmetric bins with non-symmetric bins or vice versa, is less than a weighting accorded a match of symmetric bins with symmetric bins or vice versa, and is greater than a weighting accorded a match of the non-symmetric bins with non-symmetric bins.

27. A method of iris capture, comprising:

one dimensional segmentation of an iris into a map of the iris; and

classification of the map into unaffected areas and affected areas.

28. The method of claim 27, further comprising regular shape fitting of the areas for normalization.

29. The method of claim 28, further comprising identifying the unaffected areas as symmetric areas.

30. The method of claim 29, further comprising calibrating the affected areas.

31. The method of claim 30, further comprising clustering the affected areas.

32. The method of claim 31, further comprising assigning a weighting to the unaffected areas and the affected areas.

33. The method of claim 32, wherein the affected areas are affected by one or more eyelids and/or one or more eyelashes.

34. The method of claim 33, further comprising:

assigning weights to the unaffected areas and the affected areas of the map of the iris and an enrolled map of an iris; and

wherein;

higher weights are attributed to unaffected areas of the map of the iris and the enrolled map of an iris;

lower weights are attributed to affected areas of the map of the iris and the enrolled map of an iris; and

weights between the higher weights and the lower weights are attributed to unaffected and affected areas of the map of the iris and the enrolled map of an iris.

35. A system comprising:

a first mechanism for one dimensional segmentation of an iris into a map of the iris;

a second mechanism for classification of the map into unaffected areas and affected areas;

a third mechanism for regular shape fitting of the areas for normalization; and

a fourth mechanism for identifying the unaffected areas as symmetric areas.

36. The system of claim 35, further comprising:

a fifth mechanism for assigning weights to the unaffected areas and the affected areas of bins of the map of the iris and an enrolled map of an iris; and

wherein;

higher weights are attributed to unaffected areas of the map of the iris and the enrolled map of an iris;

lower weights are attributed to affected areas of the bins of the map of the iris and the enrolled map of an iris; and

weights between the higher weights and the lower weights are attributed to unaffected and affected areas of bins of the map of the iris and the enrolled map of an iris.