Granted Patent B2

US 9,495,617 · App. 14/699,604 · Granted Nov 15, 2016

Abstract

Claims (42)

1. A computer-implemented method for creating an image product by accurately grouping faces, comprising:

receiving an initial set of n* face groups for a plurality of face images, wherein n* is a positive integer bigger than 1;

training classifiers between pairs of face groups in the initial set of n* face groups using image-product statistics by a computer processor;

classifying the plurality of face images by n*(n*−1)/2 classifiers to output binary vectors for the plurality of face images by the computer processor;

calculating a value for a similarity function using the binary vectors for each pair of the plurality of face images;

grouping the plurality of face images into modified face groups based on values of similarity functions by the computer processor; and

creating an image product based at least in part on the modified face groups.

2. The computer-implemented method of claim 1 , further comprising:

comparing a difference between the modified face groups and the initial set of n* face groups to a threshold value, wherein the image product is created based at least in part on the modified face groups if the difference is smaller than the threshold value.

3. The computer-implemented method of claim 2 , wherein if the difference is larger than the threshold value, the steps of training classifiers, classifying the plurality of face images, calculating a value for the similarity function, and grouping the plurality of face images into modified face groups are repeated to update the modified face groups.

4. The computer-implemented method of claim 1 , wherein there are an integer m number of face images in the plurality of face images, wherein the step of classifying the plurality of face images by n*(n*−1)/2 classifiers outputs m number of binary vectors.

5. The computer-implemented method of claim 1 , wherein the plurality of face images are grouped into modified face groups using non-negative matrix factorization based on values of the similarity functions.

6. The computer-implemented method of claim 1 , wherein the image-product statistics comprises frequencies of faces that appear in the plurality of face images.

7. The computer-implemented method of claim 1 , wherein the plurality of face images are extracted from images contained in one or more photo albums.

8. The computer-implemented method of claim 1 , wherein the image-product statistics comprises frequencies of faces that appear in image products.

9. The computer-implemented method of claim 1 , wherein the image-product statistics is based on if a largest modified face group is related to a VIP person.

10. A computer-implemented method for creating an image product by accurately grouping faces, comprising:

obtaining face images comprising faces of unknown individuals by a computer processor;

calculating similarity functions between pairs of face images by the computer processor;

joining face images that have values of the similarity functions above a predetermined threshold into a hypothetical face group, wherein the face images in the hypothetical face group hypothetically belong to a same person;

conducting non-negative matrix factorization on values of the similarity functions in the hypothetical face group to test truthfulness of the hypothetical face group;

identifying the hypothetical face group as a true face group if a percentage of the associated similarity functions being true is above a threshold based on the non-negative matrix factorization; and

creating an image product based at least in part on the true face group.

11. The computer-implemented method of claim 10 , further comprising:

rejecting the hypothetical face group as a true face group if the percentage of the associated similarity functions being true is below a threshold.

12. The computer-implemented method of claim 10 , wherein the step of conducting non-negative matrix factorization comprises:

forming a non-negative matrix using values of similarity functions between all different pairs of face images in the hypothetical face group,

wherein the non-negative matrix factorization is conducted over the non-negative matrix.

13. The computer-implemented method of claim 10 , wherein the similarity functions in the hypothetical face group are described in a similarity distribution function, wherein the step of conducting non-negative matrix factorization outputs a True similarity distribution function and a False similarity distribution function.

14. The computer-implemented method of claim 13 , wherein the step of identifying comprises:

comparing the similarity distribution function to the True similarity distribution function and the False similarity distribution function.

15. The computer-implemented method of claim 10 , wherein every pair of face images in the hypothetical face group has a similarity function above the predetermined threshold.

16. The computer-implemented method of claim 10 , further comprising:

joining two true face groups to form a joint face group;

conducting non-negative matrix factorization on values of similarity functions in the joint face group; and

merging the two true face groups if a percentage of the associated similarity functions being true is above a threshold in the joint face group.

17. The computer-implemented method of claim 16 , wherein the similarity functions in the joint face group are described in a similarity distribution function, wherein the step of conducting non-negative matrix factorization on values of similarity functions in the joint face group outputs a True similarity distribution function and a False similarity distribution function.

18. The computer-implemented method of claim 17 , wherein the step of identifying comprises:

comparing the similarity distribution function to the True similarity distribution function and the False similarity distribution function.

19. The computer-implemented method of claim 10 , further comprising:

detecting the faces in images; and

cropping portions of the images to produce the face images comprising faces of the unknown individuals.

Assignments (8)