FACE RECOGNITION TRAINING METHOD AND APPARATUS

• US 20090238419A1
• Filed: 05/07/2009
• Published: 09/24/2009
• Est. Priority Date: 03/05/2007
• Status: Active Grant

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: FotoNation Ireland Limited (Adeia Inc.)
• Inventors: Steinberg, Eran, Bigioi, Petronel, Corcoran, Peter
• Granted Patent: US 8,363,951 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 5/2621 Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability

Abstract

A device is trained for face recognition. A first acquired digital image of a scene includes a face. Face image data is extracted and stored in a face image library along with an unique identifier. A second acquired digital image may or may not include the face of the same person as the face in the first acquired digital image. Face recognition is applied to extracted face data of the second digital image, and the face of the first digital image is displayed as a match to the face of the second digital image when the first and second images are determined to match or the second digital image or a face therein is identified with biometric data stored along with the first digital image when the faces in the first and second images are determined to match.

Claims

1. A method of face categorization and annotation of a face image library, comprising:

acquiring with a digital image acquisition device a first digital image of a scene that includes a face;

extracting and storing in a face image library face image data corresponding to the face in the first digital image along with an unique identifier;

acquiring and extracting a second digital image that includes a face of a same person as the face in the first digital image;

applying face recognition to the second digital image;

analyzing whether the face in the second digital image matches the face in the first digital image; and

displaying the second digital image along with the first digital image, or associating the second digital image with another image stored in the face image library, or assigning and storing in the face image library the second digital image as a new face, or identifying the second digital image with biometric data stored along with the first digital image, or combinations thereof.

2. The method of claim 1, further comprising displaying the face of the first digital image as a match to the face of the second digital image when the faces in the first and second digital images are determined to match.

3. The method of claim 2, further comprising storing the second digital image, including associating the first and second digital images or faces contained therein, or both.

4. The method of claim 1, further comprising acquiring a series of preview images and extracting candidate face regions from successive frames.

5. The method of claim 1, further comprising maintaining location data and a cumulative confidence level that the candidate face region comprises a face, and based on information from the series of preview images, determining that said face is present within said digital image.

6. The method of claim 1, further comprising receiving manual input of further information relating to the face for storing with the full-size face image.

7. The method of claim 1, further comprising receiving identifying indicia manually by a user of the digital image acquisition device.

8. The method of claim 7, wherein the identifying indicia comprises a person'"'"'s name.

9. The method of claim 1, further comprising automatically cropping the face or removing one or more non-facial items from the digital image, or both, and thereby generating a full-size face image;

and wherein the storing comprises storing the full-size face image.

10. The method of claim 1, further comprising displaying a selectable set of one or more faces from the face image library as possible matches to the face of the second digital image when the faces in the selectable set are determined to have at least a predetermined probability of matching the face of the second digital image.

11. The method of claim 10, further comprising receiving a manual selection of a face from the selectable set, and storing the second digital image including associating the selected face with the second digital image or the face contained therein or both.

12. The method of claim 1, further comprising assigning the face in the second digital image as a new face when the face in the second digital image is determined not to match any face in the face image library.

13. The method of claim 1, further comprising identifying the second digital image with biometric data stored along with the first digital image.

14. One or more computer readable media encoded with a computer program for programming one or more processors to perform a method of face of face recognition training for a digital image acquisition device, the method comprising:

acquiring with a digital image acquisition device a first digital image of a scene that includes a face;

extracting and storing in a face image library face image data corresponding to the face in the first digital image along with an unique identifier;

acquiring and extracting a second digital image that includes a face of a same person as the face in the first digital image;

applying face recognition to the second digital image; and

analyzing whether the face of the first digital image is a match to the face of the second digital image.

15. The one or more computer readable media of claim 14, further comprising displaying the face of the first digital image as a match to the face of the second digital image when the faces in the first and second digital images are determined to match.

16. The one or more computer readable media of claim 15, further comprising storing the second digital image, including associating the first and second digital images or faces contained therein, or both.

17. The one or more computer readable media of claim 14, wherein the method further comprises acquiring a series of preview images and extracting candidate face regions from successive frames.

18. The one or more computer readable media of claim 17, wherein the method further comprises maintaining location data and a cumulative confidence level that the candidate face region comprises a face, and based on information from the series of preview images, determining that said face present within said digital image.

19. The one or more computer readable media of claim 14, wherein the method further comprises receiving manual input of further information relating to the face for storing with the face image data.

20. The one or more computer readable media of claim 14, wherein the method further comprises receiving identifying indicia manually by a user of the digital image acquisition device.

21. The one or more computer readable media of claim 20, wherein the identifying indicia comprises a person'"'"'s name.

22. The one or more computer readable media of claim 14, wherein the method further comprises automatically cropping the face or removing one or more non-facial items from the digital image, or both, and thereby generating a full-size face image;

and wherein the storing comprises storing the full-size face image.

23. The one or more computer readable media of claim 14, wherein the method further comprises displaying a selectable set of one or more faces from the face image library as possible matches to the face of the second digital image when the faces in the selectable set are determined to have at least a predetermined probability of matching the face of the second digital image.

24. The one or more computer readable media of claim 23, wherein the method further comprises receiving a manual selection of a face from the selectable set, and storing the second digital image including associating the selected face with the second digital image or the face contained therein or both.

25. The one or more computer readable media of claim 14, wherein the method further comprises assigning the face in the second digital image as a new face when the face in the second digital image is determined not to match any face in the face image library.

26. The one or more computer readable media of claim 14, wherein the method further comprises identifying the second digital image with biometric data stored along with the first digital image.

27. A digital image acquisition device comprising a lens, an image sensor, a processor, and a memory having embedded therein processor-readable code for programming the processor to perform a method of face of face recognition training, the method comprising:

acquiring with a digital image acquisition device a first digital image of a scene that includes a face;

extracting and storing in a face image library face image data corresponding to the face in the first digital image along with an unique identifier;

acquiring and extracting a second digital image that includes a face of a same person as the face in the first digital image;

applying face recognition to the second digital image; and

analyzing whether the face of the first digital image is a match to the face of the second digital image.

28. The device of claim 27, wherein the method further comprises displaying the face of the first digital image as a match to the face of the second digital image when the faces in the first and second digital images are determined to match.

29. The device of claim 28, wherein the method further comprises storing the second digital image, including associating the first and second digital images or faces contained therein, or both.

30. The device of claim 27, wherein the method further comprises acquiring a series of preview images and extracting candidate face regions from successive frames.

31. The device of claim 27, wherein the method further comprises maintaining location data and a cumulative confidence level that the candidate face region comprises a face, and based on information from the series of preview images, determining that said face present within said digital image.

32. The device of claim 31, wherein the method further comprises receiving manual input of further information relating to the face for storing with the face image data.

33. The device of claim 27, wherein the method further comprises receiving identifying indicia manually by a user of the digital image acquisition device.

34. The device of claim 27, wherein the identifying indicia comprises a person'"'"'s name.

35. The device of claim 27, wherein the method further comprises automatically cropping the face or removing one or more non-facial items from the digital image, or both, and thereby generating a full-size face image;

and wherein the storing comprises storing the full-size face image.

36. The device of claim 27, wherein the method further comprises displaying a selectable set of one or more faces from the face image library as possible matches to the face of the second digital image when the faces in the selectable set are determined to have at least a predetermined probability of matching the face of the second digital image.

37. The device of claim 36, wherein the method further comprises receiving a manual selection of a face from the selectable set, and storing the second digital image including associating the selected face with the second digital image or the face contained therein or both.

38. The device of claim 27, wherein the method further comprises assigning the face in the second digital image as a new face when the face in the second digital image is determined not to match any face in the face image library.

39. The device of claim 27, wherein the method further comprises identifying the second digital image with biometric data stored along with the first digital image.