Systems and methods for providing object recognition based on detecting and extracting media portions

Patent metadata

Field	Value
Publication number	US-9734387-B2
Application number	US-201514656276-A
Country	US
Kind code	B2
Filing date	Mar 12, 2015
Priority date	Mar 12, 2015
Publication date	Aug 15, 2017
Grant date	Aug 15, 2017

Abstract

Systems, methods, and non-transitory computer-readable media can receive a selection of an image. An object included in the image can be detected. An image portion that includes the object can be extracted from the image. The image portion can be provided for image analysis based on one or more object recognition processes. An identifier for the object can be received. The identifier can be determined based on the one or more object recognition processes being applied to the image portion.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving, by a computing system, a selection of an image by an uploading user;
detecting, by the computing system, an object included in the image;
extracting, by the computing system, from the image, an image portion comprising a set of pixels that includes the object;
providing, by the computing system, to one or more servers remote from the computing system the image portion for image analysis based on one or more object recognition processes performed, at least in part, via the one or more servers remote from the computing system;
receiving, by the computing system, an identifier for the object, the identifier being determined based on the one or more object recognition processes being applied to the image portion;
presenting, by the computing system, the image and the identifier to the uploading user; and
transmitting, by the computing system, the image and the identifier to a networking system in response to an upload command by the uploading user.

2. The computer-implemented method of claim 1 , further comprising:
providing the uploading user one or more options to modify the identifier.

3. The computer-implemented method of claim 1 , wherein detecting the object included in the image further comprises determining a location of the object within the image, wherein the identifier is presented based on the location of the object within the image, wherein the identifier is presented to appear to overlay the image, and wherein the identifier is presented to avoid obscuring the object included in the image.

4. The computer-implemented method of claim 1 , further comprising:
detecting a second object included in the image;
extracting, from the image, a second image portion that includes the second object; and
providing the second image portion for image analysis based on the one or more object recognition processes, wherein the image portion and the second image portion are provided in conjunction.

5. The computer-implemented method of claim 1 , wherein the object includes a face of a user represented in the image, wherein the one or more object recognition processes include one or more facial recognition processes, and wherein the identifier includes a name associated with the user.

6. The computer-implemented method of claim 5 , wherein the one or more facial recognition processes utilizes, at least in part, one or more people clustering processes.

7. The computer-implemented method of claim 5 , wherein the uploading user is associated with a set of social connections via the networking system, and wherein the one or more facial recognition processes utilizes, at least in part, one or more face models associated with a subset of social connections out of the set of social connections.

8. The computer-implemented method of claim 7 , wherein the subset of social connections includes a specified quantity of highest ranked social connections, and wherein each social connection in the set is ranked based on at least one of a social coefficient metric for each social connection relative to the uploading user, a social affinity metric for each social connection relative to the uploading user, a social interaction recency metric for each social connection relative to the uploading user, or location data associated with each social connection.

9. The computer-implemented method of claim 1 , wherein the identifier is utilized, at least in part, to define a set of images such that each image in the set includes a respective object associated with the identifier.

10. A system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
receiving a selection of an image by an uploading user;
detecting an object included in the image;
extracting, from the image, an image portion comprising a set of pixels that includes the object;
providing to one or more servers remote from the computing system the image portion for image analysis based on one or more object recognition processes performed, at least in part, via the one or more servers remote from the computing system;
receiving an identifier for the object, the identifier being determined based on the one or more object recognition processes being applied to the image portion;
presenting the image and the identifier to the uploading user; and
transmitting the image and the identifier to a networking system in response to an upload command by the uploading user.

11. The system of claim 10 , wherein the instructions cause the system to further perform:
providing the uploading user one or more options to modify the identifier.

12. The system of claim 10 , wherein the one or more object recognition processes are performed, at least in part, via one or more remote servers.

13. The system of claim 10 , wherein the object includes a face of a user represented in the image, wherein the one or more object recognition processes include one or more facial recognition processes, and wherein the identifier includes a name associated with the user.

14. The system of claim 13 , wherein the uploading user is associated with a set of social connections via the networking system, and wherein the one or more facial recognition processes utilizes, at least in part, one or more face models associated with a subset of social connections out of the set of social connections.

15. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform:
receiving a selection of an image by an uploading user;
detecting an object included in the image;
extracting, from the image, an image portion comprising a set of pixels that includes the object;
providing to one or more servers remote from the computing system the image portion for image analysis based on one or more object recognition processes performed, at least in part, via the one or more servers remote from the computing system;
receiving an identifier for the object, the identifier being determined based on the one or more object recognition processes being applied to the image portion;
presenting the image and the identifier to the uploading user; and
transmitting the image and the identifier to a networking system in response to an upload command by the uploading user.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions cause the system to further perform:
providing the uploading user one or more options to modify the identifier.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the one or more object recognition processes are performed, at least in part, via one or more remote servers.

18. The non-transitory computer-readable storage medium of claim 15 , wherein the object includes a face of a user represented in the image, wherein the one or more object recognition processes include one or more facial recognition processes, and wherein the identifier includes a name associated with the user.

19. The non-transitory computer-readable storage medium of claim 18 , wherein the uploading user is associated with a set of social connections via the networking system, and wherein the one or more facial recognition processes utilizes, at least in part, one or more face models associated with a subset of social connections out of the set of social connections.

Assignees

• Facebook Inc

Inventors

• Barak Dan
• Bar Tomer
• Chen Kun

Classifications

• G06V40/172 Primary

  Classification, e.g. identification · CPC title

• G06V20/20

  in augmented reality scenes · CPC title

• G06K9/00677

  Physics · mapped topic

• G06K9/00288 Primary

  Physics · mapped topic

• G06V20/30

  in albums, collections or shared content, e.g. social network photos or video · CPC title