Identifying Images Using Face Recognition

• US 20080130960A1
• Filed: 12/01/2006
• Published: 06/05/2008
• Est. Priority Date: 12/01/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Yagnik, Jay
• Granted Patent: US 8,085,995 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

A method includes identifying a named entity, retrieving images associated with the named entity, and using a face detection algorithm to perform face detection on the retrieved images to detect faces in the retrieved images. At least one representative face image from the retrieved images is identified, and the representative face image is used to identify one or more additional images representing the at least one named entity.

Claims

1. A method, comprising:

identifying at least one named entity;

retrieving images associated with the at least one named entity;

performing face detection on the retrieved images to detect faces in the retrieved images, wherein the face detection is performed using a face detection algorithm;

identifying at least one representative face image from the retrieved images; and

using the at least one representative face image to identify one or more additional images representing the at least one named entity.

2. The method of claim 1, further comprising receiving a search query from a user including the at least one named entity.

3. The method of claim 2, further comprising generating search results based on the search query, wherein the search results include the one or more additional images.

4. The method of claim 1, wherein the at least one named entity is a person.

5. The method of claim 4, wherein identifying the at least one named entity comprises identifying the at least one named entity from a query log or a web document.

6. The method of claim 1, wherein retrieving images associated with the at least one named entity comprises executing an image search to identify all images associated with the at least one named entity.

7. The method of claim 1, further comprising performing face matching for the detected faces in the retrieved images by comparing each detected face to each other detected face to identify faces that match a particular face image associated with the at least one named entity.

8. The method of claim 7, further comprising determining the number of faces that match the particular face image.

9. The method of claim 8, further comprising comparing the determined number of faces that match the particular face image to a threshold value.

10. The method of claim 7, further comprising determining the detected face in the retrieved images that matches the highest number of other detected faces in the retrieved images.

11. The method of claim 10, further comprising generating a training set of face images, wherein the training set includes each of the detected faces that match the particular face image associated with the at least one named entity.

12. The method of claim 11, further comprising generating at least one face model from the training set of face images.

13. The method, of claim 12, further comprising labeling the at least one face model with at least a portion of the name of the at least one named entity.

14. The method of claim 12, wherein using the at least one representative face image to identify one or more additional images comprises using the at least one face model to identify the one or more additional images.

15. The method of claim 14, wherein using the at least one face model to identify the one or more additional images comprises comparing the face model to a collection of images to identify the one or more additional images.

16. The method of claim 15, further comprising associating the one or more additional images with the at least one named entity.

17. A system, comprising:

means for identifying at least one named entity;

means for retrieving images associated with the at least one named entity;

means for performing face detection on the retrieved images to detect faces in the retrieved images;

means for identifying at least one representative face image from the retrieved images; and

means for using the at least one representative face image to identify one or more additional images representing the at least one named entity.

18. The system of claim 17, further comprising means for receiving a search query from a user including the at least one named entity.

19. The system of claim 18, further comprising means for generating search results based on the search query, wherein the search results include the one or more additional images.

20. The system of claim 17, wherein the at least one named entity is a person.

21. The system of claim 20, wherein means for identifying the at least one named entity comprises means for identifying the at least one named entity from a query log or a web document.

22. The system of claim 17, wherein means for retrieving images associated with the at least one named entity comprises means for executing an image search to identify all images associated with the at least one named entity.

23. The system of claim 17, further comprising means for performing face matching for the detected faces in the retrieved images by comparing each detected face to each other detected face to identify faces that match a particular face image associated with the at least one named entity.

24. The system of claim 23, further comprising means for determining the number of faces that match the particular face image.

25. The system of claim 24, further comprising means for comparing the determined number of faces that match the particular face image to a threshold value.

26. The system of claim 23, further comprising means for determining the detected face in the retrieved images that matches the highest number of other detected faces in the retrieved images.

27. The system of claim 26, further comprising means for generating a training set of face images, wherein the training set includes each of the detected faces that match the particular face image associated with the at least one named entity.

28. The system of claim 27, further comprising means for generating at least one face model from the training set efface images.

29. The system of claim 28, further comprising means for labeling the at least one face model with at least a portion of the name of the at least one named entity.

30. The system of claim 28, wherein means for using the at least one representative face image to identify one or more additional images comprises means for using the at least one face model to identity the one or more additional images.

31. The system of claim 30, wherein means for using the at least one face model to identify the one or more additional images comprises means for comparing the face model to a collection of images to identify the one or more additional images.

32. The system of claim 31, further comprising means for associating the one or more additional images with the at least one named entity