Method and system for tagging an image of an individual in a plurality of photos

• US 9,569,659 B2
• Filed: 02/19/2016
• Issued: 02/14/2017
• 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:
  US15/048,951
• Publication Number:
  US 20160171290A1
• Time in Patent Office: 361 Days
• Field of Search: None
• US Class Current: 1/1
• 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 tagging an image of an individual in a plurality of images, the method comprising:

providing a first plurality of images, each of the first plurality of images comprising an identified facial image of the individual;

generating a feature vector for the individual based on the identified facial image of the individual in each of the first plurality of images;

identifying each image among a second plurality of images having the facial image of the individual by matching the feature vector for the individual to a facial image of the individual in each image; and

tagging each image among the second plurality of images having the facial image of the individual with location information of the facial image of the individual in each image, wherein the location information includes X and Y coordinates of each facial image of the individual in each image, and wherein tagging includes storing an identifier for each facial image of the individual in a database and storing the X and Y coordinates for each facial image of the individual in the database.

2. The method of claim 1, wherein the first plurality of images comprises an identified object image.

3. The method of claim 1, further comprising:

analyzing the first plurality of images to determine if the identified facial image of the individual is of adequate quality.

4. The method claim 1, further comprising:

organizing each of the tagged images into a third plurality of images.

5. The method of claim 1, further comprising:

creating one or more links between tagged images.

6. The method of claim 1, wherein the plurality of images include digital images or analog images.

7. The method of claim 1, wherein the location information further includes a size of the facial image of the individual in each image.

8. The method of claim 7, wherein the location information further includes a tilt angle of the facial image of the individual in each image.

9. A system for tagging an image of an individual in a plurality of images, the system comprising:

a processor; and

one or memories in communication with the processor when the system is in operation, the one or more memories having stored thereon instructions that upon execution by the processor at least cause the system to;

provide a first plurality of images, each of the first plurality of images comprising an identified facial image of the individual;

generate a feature vector for the individual based on the identified facial image of the individual in each of the first plurality of images;

identify each image among a second plurality of images having the facial image of the individual based on a match between the feature vector for the individual and a facial image of the individual in each image; and

tag each image among the second plurality of images having the facial image of the individual with location information of the facial image of the individual in each image, wherein the location information includes X and Y coordinates of each facial image of the individual in each image, and wherein tagging includes storing an identifier for each facial image of the individual in a database and storing the X and Y coordinates for each facial image of the individual in the database.

10. The system of claim 9, wherein the first plurality of images comprises an identified object image.

11. The system of claim 9, wherein the instructions further cause the system to analyze the first plurality of images to determine if the identified facial image of the individual is of adequate quality.

12. The system claim 9, wherein the instructions further cause the system to organize each of the tagged into a third plurality of images.

13. The system of claim 9, wherein the instructions further cause the system to create one or more links between tagged images.

14. The system of claim 9, wherein the plurality of images include digital images or analog images.

15. The system of claim 9, wherein the location information further includes a size of the facial image of the individual in each image.

16. The system of claim 15, wherein the location information further includes a tilt angle of the facial image of the individual in each image.

17. A method for tagging an image of an individual in a plurality of images, the method comprising:

providing a first plurality of images, each of the first plurality of images comprising an identified facial image of the individual;

generating a feature vector for the individual based on the identified facial image of the individual in each of the first plurality of images;

identifying each image among a second plurality of images having the facial image of the individual by matching the feature vector for the individual to a facial image of the individual in each image;

tagging each image among the second plurality of images to create a third plurality of images, wherein tagging includes determining location information of the facial image of the individual in each image among the second plurality of images, wherein location information identifies a position of the facial image of the individual within each image among the second plurality of images; and

storing the location information in a database and storing an identifier for each facial image of the individual in the database.

18. The method of claim 17, wherein the position includes X and Y coordinates of each facial image of the individual in each image among the second plurality of images.

19. The method of claim 18, wherein the location information further includes a size of the facial image of the individual in each image.

20. The method of claim 18, wherein the location information further includes a tilt angle of the facial image of the individual in each image.