Method and system for tagging an individual in a digital image

• US 9,875,395 B2
• Filed: 12/02/2013
• Issued: 01/23/2018
• Est. Priority Date: 09/28/2005
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Avigilon Patent Holding 1 Corporation
• Inventors: Myers, Charles A., Shah, Alex
• Primary Examiner(s): ANSARI, TAHMINA N
• Application Number:
  US14/094,752
• Publication Number:
  US 20140093141A1
• Time in Patent Office: 1,513 Days
• Field of Search: None
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A system and method for tagging an image of an individual in a plurality of photos is disclosed herein. A feature vector of an individual is used to analyze a set of photos on a social networking website to determine if an image of the individual is present in a photo of the set of photos. Photos having an image of the individual are tagged preferably by listing a URL or URI for each of the photos in a database.

Claims

1. A method, for classifying an image of an individual, comprising:

receiving, at a server, from a computing device a photo containing an unknown facial image of the individual;

wherein the server includes a plurality of stored reference photos comprising identified facial images of individuals and, for each of a plurality of identified facial images, an identity of the individual and at least one corresponding reference feature vector generated from the identified facial images to provide a plurality of stored reference feature vectors;

determining, by the server, a set of variables with respect to facial features of the unknown facial image in the photo that are of interest for classification, wherein the set of variables comprises at least a distance between the center of the eyes to a chin;

processing, by the server, the unknown facial image of the individual in the photo to generate a subject feature vector for the individual in the photo based on the set of variables;

classifying, by the server, an identity of the unknown facial image, wherein the classifying comprises comparing the subject feature vector to one or more stored reference feature vectors to determine a match to a stored reference feature vector corresponding to the identity of the individual; and

sending, by the server, an identifier for the individual to the computing device.

2. The method of claim 1, wherein the identifier further comprises at least one of:

the name of the individual, meta-data, a matched image corresponding to the identity of the individual, and the photo containing the unknown facial image of the individual.

3. The method of claim 2, wherein the meta-data comprises at least one of:

internet references, sponsored links, and advertisements.

4. The method of claim 2, further comprising prior to sending the matched image corresponding to the identity of the individual as the identifier, manipulating the matched image to emphasize matching characteristics with respect to the photo containing the unknown facial image of the individual.

5. The method of claim 1, wherein classifying further comprises finding one of the plurality of identified facial images corresponding to the identity of the individual to use as the matched image.

6. The method of claim 1, wherein the photo is either a digital image or an analog image.

7. The method of claim 1, wherein the plurality of stored reference photos comprises multiple photos of at least one individual in different poses and facial expressions.

8. The method of claim 1, further comprising, upon classifying the identity of the unknown facial image, storing the subject feature vector for subsequent use in identifying a facial image of the individual in one or more other photos.

9. The method of claim 8, further comprising combining the subject feature vector and at least one corresponding reference feature vector of the individual for subsequent use in identifying a facial image of the individual in one or more other photos.

10. The method of claim 1, wherein the computing device is a computer or a mobile telephone.

11. A system for classifying an image of an individual, comprising:

a server configured to receive from a computing device a photo containing an unknown facial image of an individual, wherein the server includes a plurality of stored reference photos comprising identified facial images of individuals and, for each of a plurality of identified facial images, an identity of the individual and at least one corresponding reference feature vector generated from the identified facial images to provide a plurality of stored reference feature vectors, and wherein the server further includes instructions executable by the server that when executed cause the server to;

determine a set of variables with respect to facial features of the unknown facial image in the photo that are of interest for classification, wherein the set of variables comprises at least a distance between the center of the eyes to a chin;

process the unknown facial image of the individual in the photo to generate a subject feature vector for the individual in the photo based on the set of variables;

classify an identity of the unknown facial image, wherein classify comprises comparing the subject feature vector to one or more stored reference feature vectors to determine a match to a stored reference feature vector corresponding to the identity of the individual; and

send an identifier for the individual to the computing device.

12. The system of claim 11, wherein the identifier further comprises at least one of:

the name of the individual, meta-data, a matched image corresponding to the identity of the individual, and the photo containing the unknown facial image of the individual.

13. The system of claim 12, wherein the meta-data comprises at least one of:

internet references, sponsored links, and advertisements.

14. The system of claim 12, wherein the instructions cause the server, prior to sending the matched image corresponding to the identity of the individual, to manipulate the matched image to emphasize matching characteristics with respect to the photo containing the unknown facial image of the individual.

15. The system of claim 11, wherein the photo is either a digital image or an analog image.

16. The system of claim 11, wherein the plurality of stored reference photos comprises multiple photos of at least one individual in different poses and facial expressions.

17. The system of claim 11, wherein the instructions cause the server, upon classifying the identity of the unknown facial image, to store the subject feature vector for subsequent use in identifying a facial image of the individual in one or more other photos.

18. The system of claim 11, wherein the instructions cause the server to combine the subject feature vector and at least one corresponding reference feature vector of the individual for subsequent use in identifying a facial image of the individual in one or more other photos.