Face Recognition System and Method

• US 20110091080A1
• Filed: 06/24/2009
• Published: 04/21/2011
• Est. Priority Date: 07/02/2008
• Status: Active Grant

• Current Assignee: C-True Limited
• Original Assignee: C-True Limited
• Inventors: Freitsis, Ester, Goldenberg, Shmuel, Gamliel, Avihu Meir, Tsipis, Felix, Kheifetz, Yuri
• Granted Patent: US 8,600,121 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06V 10/95 structured as a network, e.g. client-server architectures
• CPC Class Codes: G06V 40/164 using holistic features
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships

Abstract

Apparatus for face recognition, the apparatus comprising: a face symmetry verifier, configured to verify symmetry of a face in at least one image, according to a predefined symmetry criterion, and a face identifier, associated with the face symmetry verifier, and configured to identify the face, provided the symmetry of the face is successfully verified.

Claims

1. Apparatus for face recognition, the apparatus comprising:

a face symmetry verifier, configured to verify symmetry of a face in at least one image, according to a predefined symmetry criterion; and

a face identifier, associated with said face symmetry verifier, and configured to identify said face, provided said symmetry of said face is successfully verified.

2. The apparatus of claim 1, further comprising an image capturer, associated with said face symmetry verifier, and configured to capture said image of said face.

3. The apparatus of claim 1, further comprising a face detector, associated with said face symmetry verifier, and configured to detect said face in said image.

4. The apparatus of claim 3, wherein said face detector is further configured to use a skin detection method, for detecting said face in said image.

5. The apparatus of claim 3, wherein said face detector is further configured to use a Viola-Jones detection method, for detecting said face in said image.

6. The apparatus of claim 3, wherein said face detector is further configured to use a Gabor Filter based method, for detecting said face in said image.

7. The apparatus of claim 1, further comprising an image cropper, associated with said face symmetry verifier, and configured to crop said image, thereby to remove background from said image.

8. The apparatus of claim 1, further comprising an image resizer, associated with said face symmetry verifier, and configured to resize said image into a predefined size.

9. The apparatus of claim 1, further comprising an image illumination quality improver, associated with said face symmetry verifier, and configured to improve a quality of illumination of said image.

10. The apparatus of claim 9, wherein said image illumination quality improver is further configured to use Histogram Equalization, for improving said quality of illumination of said image.

11. The apparatus of claim 1, wherein said face symmetry verifier is further configured to use an intensity map, for verifying said symmetry of said face in said image.

12. The apparatus of claim 1, wherein said face symmetry verifier is further configured to use a gradient map, for verifying said symmetry of said face in said image.

13. The apparatus of claim 1, wherein said face symmetry verifier is further configured to use a Fourier Transform phase map, for verifying said symmetry of said face in said image.

14. The apparatus of claim 1, wherein said face symmetry verifier is further configured to measure symmetry of each one of a plurality of input images, and select said at least one image of said face among said plurality of input images, and wherein said measured symmetry of said at least one selected image of said face is highest amongst said input images.

15. The apparatus of claim 14, wherein said plurality of input images are at least a part of a video sequence.

16. Apparatus for face recognition, the apparatus comprising:

a face symmetry verifier, configured to verify symmetry of a face in at least one first image of said face, according to a predefined symmetry criterion, wherein said first image is associated with respective data identifying said face; and

a face database updater, associated with said face symmetry verifier, and configured to update a face database with said first image of said face and said associated data identifying said face, provided said symmetry of said face in said first image is successfully verified.

17. The apparatus of claim 16, wherein said face symmetry verifier is further configured to verify symmetry of said face in at least one second image of said face, according to said predefined symmetry criterion;

the apparatus further comprising a face identifier, associated with said face symmetry verifier and configured to identify said face in said second image, using said face database, provided said symmetry of said face in said second image is successfully verified.

18. Apparatus for face recognition, the apparatus comprising:

a face symmetry verifier, configured to verify symmetry of a face in at least one image, according to a predefined symmetry criterion; and

a forwarding controller, associated with said face symmetry verifier, and configured to control forwarding of said image, according to a result of said verification of said symmetry by said face symmetry verifier.

19. Method for face recognition, the method comprising:

a) verifying symmetry of a face in at least one image, according to a predefined symmetry criterion; and

b) identifying said face, provided said symmetry of said face is successfully verified.

20. The method of claim 19, further comprising capturing said image of said face.

21. The method of claim 19, further comprising detecting said face in said image.

22. The method of claim 21, further comprising using a skin detection method, for detecting said face in said image.

23. The method of claim 21, further comprising using a Viola-Jones detection method, for detecting said face in said image.

24. The method of claim 21, further comprising using a Gabor Filter based method, for detecting said face in said image.

25. The method of claim 19, further comprising cropping said image, thereby removing background from said image.

26. The method of claim 19, further comprising resizing said image into a predefined size.

27. The method of claim 19, further comprising improving a quality of illumination of said image.

28. The method of claim 27, further comprising using Histogram Equalization, for improving said quality of illumination of said image.

29. The method of claim 19, further comprising using an intensity map, for verifying said symmetry of said face in said image.

30. The method of claim 19, further comprising using a gradient map, for verifying said symmetry of said face in said image.

31. The method of claim 19, further comprising using a Fourier Transform phase map, for verifying said symmetry of said face in said image.

32. The method of claim 19, further comprising measuring symmetry of each one of a plurality of input images, and selecting said at least one image of said face among said plurality of input images, and wherein said measured symmetry of said at least one selected image of said face is highest amongst said input images.

33. The method of claim 32, wherein said plurality of input images are at least a part of a video sequence.

34. Method for face recognition, the method comprising:

a) verifying symmetry of a face in at least one first image of said face, according to a predefined symmetry criterion, wherein said first image is associated with respective data identifying said face; and

b) updating a face database with said first image of said face and said associated data identifying said face, provided said symmetry of said face in said first image is successfully verified.

35. The method of claim 34, further comprising:

c) verifying symmetry of said face in at least one second image of said face, according to said predefined symmetry criterion; and

d) identifying said face in said second image, using said face database, provided said symmetry of said face in said second image is successfully verified.

36. Method for face recognition, the method comprising:

a) verifying symmetry of a face in at least one image, according to a predefined symmetry criterion; and

b) controlling forwarding of said image, according to a result of said verifying of said symmetry.