Networked Face Recognition System

• US 20100329568A1
• Filed: 06/24/2009
• Published: 12/30/2010
• Est. Priority Date: 07/02/2008
• Status: Abandoned Application

• Current Assignee: C-True Limited
• Original Assignee: C-True Limited
• Inventors: Freitsis, Ester, Goldenberg, Shmuel, Gamliel, Avihu Meir, Tsipis, Felix, Kheifetz, Yuri
• Application Number:
  US12/919,092
• Publication Number:
  US 20100329568A1
• Time in Patent Office: Days
• US Class Current: 382/190
• 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

A networked system for face recognition, the system comprising: a face verifier, configured to verify compliance of a face in an image with at least one predefined criterion, and upon successful verification of the compliance, to forward the image for feature extraction, a feature extractor, associated with the face verifier, configured to extract a feature from the forwarded image; and a face identifier, communicating with the feature extractor over a network, configured to receive the extracted feature and identify the face in the forwarded image, using the extracted feature.

Claims

1. A networked system for face recognition, the system comprising:

a face verifier, configured to verify compliance of a face in an image with at least one predefined criterion, and conditioned upon compliance of the face with a predefined criterion, to forward the image for feature extraction;

a feature extractor, associated with said face verifier, configured to extract a feature from the forwarded image; and

a face identifier, communicating with said feature extractor over a network, configured to receive the extracted feature and identify the face in the forwarded image, using the extracted feature.

2. The networked system of claim 1, wherein said network is a wide area network.

3. The networked system of claim 1, wherein said network is the internet.

4. The networked system of claim 1, wherein the predefined criterion is indicative of symmetry of the face.

5. A networked system for face recognition, the system comprising:

a face verifier, configured to verify compliance of a face in an image with at least one predefined criterion, and conditioned upon compliance of the face with a predefined criterion, to send the image over a network;

a feature extractor, communicating with said face verifier over the network, and configured to receive said sent image and extract a feature from said received image; and

a face identifier, associated with said feature extractor and configured to identify the face in the received image, using the extracted feature.

6. The networked system of claim 5, wherein said network is a wide area network.

7. The networked system of claim 5, wherein said network is the Internet.

8. A networked system for face recognition, the system comprising:

a face verifier, configured to verify compliance of a face in an image with at least one predefined criterion, and conditioned upon compliance of the face with a predefined criterion, to send the image over a first network;

a feature extractor, communicating with said face verifier over the first network, configured to receive said sent image, extract a feature from said received image, and sent said extracted feature over a second network; and

a face identifier, communicating with said feature extractor over the second network, configured to receive the extracted feature and identify the face in the received image, using the extracted feature.

9. The networked system of claim 8, wherein at least one of said first and second network is a wide area network.

10. The networked system of claim 8, wherein at least one of said first and second network is the internet.

11. A networked system for face recognition, the system comprising:

a face verifier, configured to verify compliance of a face in an image with at least one predefined criterion, and conditioned upon compliance of the face with a predefined criterion, to send data comprising at least a part of the image over a network; and

a face identifier, communicating with said face verifier over the network, configured to receive the sent data and identify the face, using at least a part of the received data.

12. The networked system of claim 11, wherein said network is a wide area network.

13. The networked system of claim 11, wherein said network is the internet.

14. The networked system of claim 11, wherein said network is an intranet network.

15. The networked system of claim 11, further comprising an image capturer, associated with said face verifier, and configured to capture said image of said face.

16. The networked system of claim 11, further comprising a face detector, associated with said face verifier, and configured to detect said face in said image.

17. The networked system of claim 16, wherein said face detector is further configured to use a skin detection method, for detecting said face in said image.

18. The networked system of claim 16, wherein said face detector is further configured to use a Viola-Jones detection method, for detecting said face in said image.

19. The networked system of claim 16, wherein said face detector is further configured to use a Gabor Filter based method, for, detecting said face in said image.

20. The networked system of claim 11, further comprising an image cropper, associated with said face verifier, and configured to crop said image, thereby to remove background from said image.

21. The networked system of claim 11 further comprising an image resizer, associated with said face verifier, and configured to resize said image into a predefined size.

22. The networked system of claim 11, further comprising an image illumination quality improver, associated with said face verifier, and configured to improve a quality of illumination of said image.

23. The networked system of claim 22, wherein said image illumination quality improver is further configured to use Histogram Equalization, for improving said quality of illumination of said image.

24. The networked system of claim 11, wherein said face verifier is further configured to use an intensity map, for verifying the compliance of the face with the predefined criterion.

25. The networked system of claim 11, wherein said face verifier is further configured to use a gradient map, for verifying the compliance of the face with the predefined criterion.

26. The networked system of claim 11, wherein said face verifier is further configured to use a Fourier Transform phase map, for verifying the compliance of the face with the predefined criterion.

27. The networked system of claim 11, wherein said face verifier is further configured to measure said compliance of said face in each one of a plurality of input images, and select at least one image of said face among said plurality of input images, and wherein said measured compliance of said face in said at least one selected image of said face is highest amongst said input images.

28. The networked system of claim 27, wherein said plurality of input images are at least a part of a video sequence.

29. A networked system for face recognition, the system comprising:

a face verifier, configured to verify compliance of a face in an image with at least one predefined criterion, and conditioned upon compliance of the face with a predefined criterion, to send data comprising at least a part of the image over a network; and

a face database updater, communicating with said face verifier over the network, and configured to receive the sent data and update a face database with at least a part of the received data.

30. The networked system of claim 29, wherein said network is a wide area network.

31. A networked system for face recognition, the networked system comprising:

a face verifier, configured to verify compliance of a face in an image with at least one predefined criterion, and restrict forwarding of data comprising at least a part of the image over a network, according to results of the verification of the compliance.

32. Method for face recognition, the method comprising:

a) verifying compliance of a face in an image with a predefined criterion;

b) sending data comprising at least a part of the image over a network, for identification, said sending conditioned upon compliance of the face with the predefined criterion; and

c) identifying the face in the image, using at least a part of the sent data.

33. The method of claim 32, further comprising capturing said image of said face.

34. The method of claim 32, further comprising detecting said face in said image.

35. The method of claim 32, further comprising using a skin detection method, for detecting said face in said image.

36. The method of claim 32, further comprising using a Viola-Jones detection method, for detecting said face in said image.

37. The method of claim 32, further comprising using a Gabor Filter based method, for detecting said face in said image.

38. The method of claim 32, further comprising cropping said image, thereby removing background from said image.

39. The method of claim 32, further comprising resizing said image into a predefined size.

40. The method of claim 32, further comprising improving a quality of illumination of said image.

41. The method of claim 40, further comprising using Histogram Equalization, for improving said quality of illumination of said image.

42. The method of claim 32, further comprising using an intensity map, for verifying the compliance with the predefined criterion.

43. The method of claim 32, further comprising using a gradient map, for verifying the compliance with the predefined criterion.

44. The method of claim 32, further comprising using a Fourier Transform phase map, for verifying the compliance with the predefined criterion.

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

46. The method of claim 45, wherein said plurality of input images are at least a part of a video sequence.

47. Method for face recognition, the method comprising:

a) verifying compliance of a face in an image with a predefined criterion;

b) sending data comprising at least a part of the image over a network, said sending conditioned upon compliance of the face with a predefined criterion; and

c) updating a database of images with at least a part of the sent data.

48. The method of claim 47, wherein said network is a wide area network.

49. Method for face recognition, the method comprising:

a) verifying compliance of a face in an image with a predefined criterion; and

b) controlling forwarding of data comprising at least a part of the image through a network, according to a result of said verifying of the compliance.