Granted Patent B2

US 9,773,160 · App. 14/061,522 · Granted Sep 26, 2017

Abstract

Claims (83)

1. A method for recognizing faces within images, the method comprising:

determining, by at least one processor, a set of search result images based on at least one query face, the set of search result images including a search result image that includes a representation of a face that is determined to match the query face;

providing an indication of the set of search result images to a user;

receiving an implicit indication of the accuracy of search result images based on the user's interaction with at least one of the provided search result images;

determining, by the at least one processor, that a face in the at least one search result image matches the query face based on at least the implicit indication; and

updating the set of search result images based on the determination that the face in the at least one search result image matches the query face.

2. The method of claim 1 wherein determining a set of search result images comprises:

creating a query feature vector for the query face;

forming a set of search feature vectors by creating one or more search feature vectors for faces within a set of search faces;

determining distances between the query feature vector and the search feature vectors;

selecting one or more search feature vectors that are within a selected distance of the query face feature vector; and

designating images that include faces that correspond to the selected search feature vectors as the set of search result images.

3. The method of claim 2 wherein determining distances between the query feature vector and the search feature vectors comprises determining, with the at least one processor, a weighted Euclidean distance between the query face feature vector and each of the search feature vectors.

4. The method of claim 1 further comprising accessing inferred additional feedback associated with the query face, the inferred additional feedback including information about faces in the search result images other than the face in the at least one search result image.

5. The method of claim 1 , further comprising:

accessing a set of images that include faces that have not been labeled;

sorting the set of images into groups based on the faces within the images, wherein the images in a group include faces that are determined to be the same; and

accessing the query face after the set of images have been sorted, wherein the query face is a face that is included in an image in one of the groups.

6. The method of claim 2 , further comprising:

accessing multiple query faces;

creating a query feature vector for each of the multiple faces; and

determining distances between the multiple query feature vectors and the search feature vectors.

7. The method of claim 2 , further comprising:

identifying negative faces that are determined to not match the query face; and

creating negative feature vectors for the negative faces,

wherein:

accessing at least one query face comprises accessing multiple query faces;

creating a query feature vector for the query face comprises creating a query feature vector for each of the multiple faces; and

determining distances between the query feature vector and the search feature vectors comprises distances between the multiple query feature vectors and the search feature vectors and determining distances between the negative feature vectors and the search feature vectors.

8. The method of claim 1 , wherein updating the set of search result images comprises updating the set of search result images based on inferred additional feedback.

9. A non-transitory computer-useable medium storing a computer program, the computer program including a set of instructions that are executable by at least one processor to cause the at least processor to:

determine a set of search result images based on at least one query face, the set of search result images including a search result image that includes a representation of a face that is determined to match the query face;

provide an indication of the set of search result images to a user;

receive an implicit indication of the accuracy of search result images based on the user's interaction with at least one of the provided search result images;

determine that a face in the at least one search result image matches the query face based on at least the implicit indication; and

update the set of search result images based on the determination that the face in the at least one search result image matches the query face.

10. The computer-useable medium of claim 9 wherein the set of instructions further cause the at least one processor to:

create a query feature vector for the query face;

form a set of search feature vectors by creating one or more search feature vectors for faces within a set of search faces;

determine distances between the query feature vector and the search feature vectors;

select one or more search feature vectors that are within a selected distance of the query face feature vector; and

designate images that include faces that correspond to the selected search feature vectors as the set of search result images.

11. The computer-useable medium of claim 10 wherein the set of instructions further cause the at least one processor to:

determine a weighted Euclidean distance between the query face feature vector and each of the search feature vectors.

12. The computer useable medium of claim 9 wherein the set of instructions further cause the at least one processor to:

access inferred additional feedback associated with the query face, the inferred additional feedback including information about faces in the search result images other than the face in the at least one search result image.

13. The computer useable medium of claim 9 wherein the set of instructions further cause the at least one processor to:

access a set of images that include faces that have not been labeled;

sort the set of images into groups based on the faces within the images, wherein the images in a group include faces that are determined to be the same; and

access the query face after the set of images have been sorted, wherein the query face is a face that is included in an image in one of the groups.

14. The computer-useable medium of claim 10 wherein the set of instructions further cause the at least one processor to:

access multiple query faces;

create a query feature vector for each of the multiple faces; and

determine distances between the multiple query feature vectors and the search feature vectors.

15. The computer-useable medium of claim 10 wherein the set of instructions further cause the at least one processor to:

accessing multiple query faces;

identify negative faces that are determined to not be the same as the query face; and

create negative feature vectors for the negative faces;

create a query feature vector for each of the multiple faces; and

determine distances between the multiple query feature vectors and the search feature vectors and determine distances between the negative feature vectors and the search feature vectors.

16. The computer useable medium of claim 9 wherein the set of instructions further cause the at least one processor to:

update the set of search result images based on inferred additional feedback.

17. A system for recognizing faces within images, comprising:

a memory device storing a plurality of instructions; and

at least one processor that executes the plurality of instructions to cause the at least one processor to:

determine a set of search result images based on at least one query face, the set of search result images including a search result image that includes a representation of a face that is determined to match the query face;

provide an indication of the set of search result images to a user;

receive an implicit indication of the accuracy of the search result images based on the user's interaction with

at least one of the provided search result images;

determine that a face in the at least one search result image matches the query face based on at least the implicit indication; and

update the set of search result images based on the determination that the face in the at least one search result image matches the query face.

18. The system of claim 17 wherein the at least one processor further executes the plurality of instructions to:

create a query feature vector for the query face;

form a set of search feature vectors by creating one or more search feature vectors for faces within a set of search faces;

determine distances between the query feature vector and the search feature vectors;

select one or more search feature vectors that are within a selected distance of the query face feature vector; and

designate images that include faces that correspond to the selected search feature vectors as the set of search result images.

19. The system of claim 17 wherein the at least one processor further executes the plurality of instructions to:

access inferred additional feedback associated with the query face, the inferred additional feedback including information about faces in the search result images other than the face in the at least one search result image.

20. The system of claim 17 , wherein the at least one processor further executes the plurality of instructions to:

access a set of images that include faces that have not been labeled;

sort the set of images into groups based on the faces within the images, wherein the images in a group include faces that are determined to be the same; and

access the query face after the set of images have been sorted, wherein the query face is a face that is included in an image in one of the groups.

Assignments (8)