SYSTEMS AND METHODS FOR DETERMINING USERS ASSOCIATED WITH DEVICES BASED ON FACIAL RECOGNITION OF IMAGES

• US 20190019012A1
• Filed: 07/17/2017
• Published: 01/17/2019
• Est. Priority Date: 07/17/2017
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Huang, Xun Wilson, Sun, Jun, Wang, Zhiyang, Lin, Wenjie, Yu, Jieqi, Khan, Farhan
• Granted Patent: US 10,445,558 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/50 of still image data
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/784 the detected or recognised objects being people
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

Systems, methods, and non-transitory computer readable media can identify a user associated with a device based on a subset of media content items on the device based at least in part on analysis of the subset of media content items. A relationship between the user and one or more other users depicted in the media content items can be determined. A recommendation relating to sending at least one media content item on the device to at least of the one or more other users can be generated based on the determined relationship.

Claims

1. A computer-implemented method comprising:

identifying, by a computing system, a user associated with a device based on a subset of media content items on the device based at least in part on analysis of the subset of media content items;

determining, by the computing system, a relationship between the user and one or more other users depicted in the media content items; and

generating, by the computing system, a recommendation relating to sending at least one media content item on the device to at least one of the one or more other users, based on the determined relationship.

2. The computer-implemented method of claim 1, further comprising identifying the subset of media content items, wherein the subset of media content items are selfies.

3. The computer-implemented method of claim 2, wherein the selfies are identified based on one or more of:

a resolution associated with a media content item, a machine learning model, or a camera used to capture a media content item.

4. The computer-implemented method of claim 3, wherein the machine learning model is trained to determine attributes associated with visual content of media content items.

5. The computer-implemented method of claim 2, further comprising:

generating one or more clusters of one or more faces detected in the selfies; and

identifying a cluster of the one or more clusters that has a highest distribution of faces as being associated with the user associated with the device.

6. The computer-implemented method of claim 5, further comprising generating a facial model for the user associated with the device based on the cluster associated with the user associated with the device.

7. The computer-implemented method of claim 1, further comprising:

generating one or more clusters of faces detected in the media content items; and

generating a facial model for each of the one or more clusters, wherein each of the one or more clusters is associated with a person.

8. The computer-implemented method of claim 1, wherein the recommendation indicates one or more media content items to send to a particular user of the one or more other users.

9. The computer-implemented method of claim 1, wherein the recommendation indicates at least some of the one or more other users as potential recipients of a media content item.

10. The computer-implemented method of claim 1, wherein the recommendation indicates a user of the one or more other users that is not depicted in a media content item as a potential recipient of the media content item.

11. A system comprising:

at least one hardware processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform;

identifying a user associated with a device based on a subset of media content items on the device based at least in part on analysis of the subset of media content items;

determining a relationship between the user and one or more other users depicted in the media content items; and

generating a recommendation relating to sending at least one media content item on the device to at least one of the one or more other users, based on the determined relationship.

12. The system of claim 11, wherein the instructions further cause the system to perform identifying the subset of media content items, wherein the subset of media content items are selfies.

13. The system of claim 12, wherein the selfies are identified based on one or more of:

a resolution associated with a media content item, a machine learning model, or a camera used to capture a media content item.

14. The system of claim 12, wherein the instructions further cause the system to perform:

generating one or more clusters of one or more faces detected in the selfies; and

identifying a cluster of the one or more clusters that has a highest distribution of faces as being associated with the user associated with the device.

15. The system of claim 11, wherein the recommendation indicates a user of the one or more other users that is not depicted in a media content item as a potential recipient of the media content item.

16. A non-transitory computer readable medium including instructions that, when executed by at least one hardware processor of a computing system, cause the computing system to perform a method comprising:

identifying a user associated with a device based on a subset of media content items on the device based at least in part on analysis of the subset of media content items;

determining a relationship between the user and one or more other users depicted in the media content items; and

generating a recommendation relating to sending at least one media content item on the device to at least one of the one or more other users, based on the determined relationship.

17. The non-transitory computer readable medium of claim 16, wherein the method further comprises identifying the subset of media content items, wherein the subset of media content items are selfies.

18. The non-transitory computer readable medium of claim 17, wherein the selfies are identified based on one or more of:

a resolution associated with a media content item, a machine learning model, or a camera used to capture a media content item.

19. The non-transitory computer readable medium of claim 17, wherein the method further comprises:

generating one or more clusters of one or more faces detected in the selfies; and

identifying a cluster of the one or more clusters that has a highest distribution of faces as being associated with the user associated with the device.

20. The non-transitory computer readable medium of claim 16, wherein the recommendation indicates a user of the one or more other users that is not depicted in a media content item as a potential recipient of the media content item.