IP Library Granted Patent US 9,122,912
Granted Patent B1
US 9,122,912 · App. 13/802,270 · Granted Sep 1, 2015

Sharing photos in a social network system

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,122,912
App. No.
13/802,270
Granted
Sep 1, 2015
Kind
B1
Abstract

Embodiments generally relate to sharing photos in a social network system. In one embodiment, a method includes obtaining a plurality of photos associated with a target user in a social network system, and detecting a face of one or more persons in the plurality of photos. The method also includes computing significance values for the faces, where each significance value indicates a degree of significance between the target user and each person represented by each face. The method also includes generating a significance ranking of the significance values, and determining a group of photos for the target user based on the significance ranking.

Claims (55)

1. A method comprising:

obtaining a plurality of photos associated with a target user in a social network system;

detecting a face of one or more persons in the plurality of photos, wherein the detecting of each face includes applying a face detection algorithm;

computing significance values for the faces, wherein each significance value indicates a degree of significance between the target user and each person represented by each face;

generating a significance ranking of the significance values;

determining a group of photos for the target user based on the significance ranking, wherein the determining of the group of photos includes applying a clustering algorithm to consolidate multiple appearances of a same face in the plurality of photos, and wherein the applying of the clustering algorithm includes:

determining a quality value for each photo that includes the same face, wherein the quality value is based on a combined score of two or more of a face detection confidence score, size, visibility, sharpness, and a facial orientation estimate;

generating a quality ranking of the quality values; and

selecting a representative photo to represent the same face in the group of photos based on the quality ranking;

transmitting the group of photos to the target user; and

enabling the target user to take one or more predetermined actions associated with one or more photos of the group of photos.

2. The method of claim 1 , wherein the significance values are based on one or more of a frequency that each face appears in the photos and a type of social connection between that target user and each person associated with each face.

3. The method of claim 1 ,

wherein the selecting of the representative photo to represent the same face in the group of photos comprises:

ranking the selected representative faces based on their frequency as a first ordering; and

ranking the selected representative faces based on their quality ranking as a second ordering.

4. The method of claim 1 , wherein the one or more predetermined actions comprise sharing one or more of the photos with people whose faces are shown in the photos.

5. The method of claim 1 , wherein the one or more predetermined actions comprise tagging one or more of the photos.

6. A method comprising:

obtaining a plurality of photos associated with a target user in a social network system;

detecting a face of one or more persons in the plurality of photos;

computing significance values for the faces, wherein each significance value indicates a degree of significance between the target user and each person represented by each face;

generating a significance ranking of the significance values; and

determining a group of photos for the target user based on the significance ranking, wherein the determining of the group of photos includes applying a clustering algorithm to consolidate multiple appearances of a same face in the plurality of photos, and wherein the applying of the clustering algorithm includes:

determining a quality value for each photo that includes the same face, wherein the quality value is based on a combined score of two or more of a face detection confidence score, size, visibility, sharpness, and a facial orientation estimate;

generating a quality ranking of the quality values; and

selecting a representative photo to represent the same face in the group of photos based on the quality ranking.

7. The method of claim 6 , wherein the significance value for each face is based on one or more of a frequency that each face appears in the plurality of photos and a type of social connection between that target user and each person associated with each face.

8. The method of claim 6 , further comprising transmitting the group of photos to the target user.

9. The method of claim 6 , further comprising:

transmitting the group of photos to the target user; and

prompting the target user with a sharing option to share one or more of the photos with people whose faces are shown in the photos.

10. The method of claim 6 , further comprising:

transmitting the group of photos to the target user; and

prompting the target user with a tagging option to tag one or more of the photos.

11. The method of claim 6 , wherein the determining of the group of photos is based at least in part on a predetermined quality criteria.

12. A system comprising:

one or more processors; and

logic encoded in one or more tangible media for execution by the one or more processors and when executed operable to perform operations comprising:

obtaining a plurality of photos associated with a target user in a social network system;

detecting a face of one or more persons in the plurality of photos;

computing significance values for the faces, wherein each significance value indicates a degree of significance between the target user and each person represented by each face;

generating a significance ranking of the significance values; and

determining a group of photos for the target user based on the significance ranking, wherein the determining of the group of photos includes applying a clustering algorithm to consolidate multiple appearances of a same face in the plurality of photos, and wherein the applying of the clustering algorithm includes:

determining a quality value for each photo that includes the same face, wherein the quality value is based on a combined score of two or more of a face detection confidence score, size, visibility, sharpness, and a facial orientation estimate;

generating a quality ranking of the quality values; and

selecting a representative photo to represent the same face in the group of photos based on the quality ranking.

13. The system of claim 12 , wherein the significance value for each face is based on one or more of a frequency that each face appears in the plurality of photos and a type of social connection between that target user and each person associated with each face.

14. The system of claim 12 , wherein the logic when executed is further operable to perform operations comprising transmitting the group of photos to the target user.

15. The system of claim 12 , wherein the logic when executed is further operable to perform operations comprising:

transmitting the group of photos to the target user; and

prompting the target user with a sharing option to share one or more of the photos with people whose faces are shown in the photos.

16. The system of claim 12 , wherein the logic when executed is further operable to perform operations comprising:

transmitting the group of photos to the target user; and

prompting the target user with a tagging option to tag one or more of the photos.

Assignments (2)
CHANGE OF NAME Recorded Oct 2, 2017
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 044334/0466 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 19, 2013
From: BRISKIN, GIL SIMHA; ZOMET, ASAF
To: GOOGLE INC.
Reel/Frame 030040/0301 →