Grouping face images using statistic distribution estimate

Patent metadata

Field	Value
Publication number	US-9280701-B2
Application number	US-201414272809-A
Country	US
Kind code	B2
Filing date	May 8, 2014
Priority date	May 8, 2014
Publication date	Mar 8, 2016
Grant date	Mar 8, 2016

Abstract

A computer-implemented method for sorting face images of different individuals into different groups includes 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; and 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.

First claim

The invention claimed is:

1. A computer-implemented method for sorting face images of different individuals into different groups, 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; and
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.

2. The computer-implemented method of claim 1 , further comprising:
rejecting the hypothetical face group as a true face group if a percentage of the associated similarity functions being true is below a threshold.

3. The computer-implemented method of claim 1 , 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.

4. The computer-implemented method of claim 1 , wherein the similarity functions in the hypothetical face group are described in a similarity distribution function, wherein the step of non-negative matrix factorization outputs a True similarity distribution function and a False similarity distribution function.

5. The computer-implemented method of claim 4 , wherein the step of identifying comprises:
comparing the similarity distribution function to the True similarity distribution function and the False similarity distribution function.

6. The computer-implemented method of claim 1 , wherein every pair of face images in the hypothetical face group has a similarity function above the predetermined threshold.

7. The computer-implemented method of claim 1 , 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.

8. The computer-implemented method of claim 7 , 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.

9. The computer-implemented method of claim 8 , wherein the step of identifying comprises:
comparing the similarity distribution function to the True similarity distribution function and the False similarity distribution function.

10. The computer-implemented method of claim 1 , further comprising:
detecting the faces in images; and
cropping portions of the images to produce the face images comprising faces of the unknown individuals.

Assignees

• Shutterfly Inc

Inventors

• Sandler Roman
• Kenis Alexander M

Classifications

• G06V10/763

  Non-hierarchical techniques, e.g. based on statistics of modelling distributions · CPC title

• G06V40/161

  Detection; Localisation; Normalisation · CPC title

• G06V40/172 Primary

  Classification, e.g. identification · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06F18/2321

  using statistics or function optimisation, e.g. modelling of probability density functions · CPC title