Method and system for automatically cropping images
View Patent ↗An image cropping technique includes detecting, at a computer system including one or more processors, faces within an image and evaluating, at the computer system, the faces to determine if any of the faces correspond to people within a user's online social network. The technique additionally includes defining, at the computer system, a first crop region including a subset of the faces when at least one face within the subset of the faces corresponds to a first person in the user's online social network and cropping, at the computer system, the image based on the first crop region.
1. A computer-implemented method to crop an image, the method comprising:
detecting, by a computer system including one or more processors, one or more faces within an image;
evaluating, by the computer system, the one or more faces to identify a subset of faces each corresponding to a person within a user's online social network;
determining, by the computer system, a degree of affiliation between the user and each person in the subset of the faces within the user's online social network;
determining, by the computer system, saliency values of pixels within the image;
adjusting, by the computer system, the saliency values of pixels within the image based on the determined degree of affiliation; and
cropping, by the computer system, the image based on the adjusted saliency values.
2. The method of claim 1 , further comprising, defining, by the computer system, a first crop region including the subset of the one or more faces based on the adjusted saliency values.
3. The method of claim 2 , wherein the crop region is defined to exclude faces that correspond to persons not within the user's online social network.
4. The method of claim 2 , wherein the cropping further comprises cropping, by the computer system, the image based on the first crop region.
5. The method of claim 1 , wherein determining the degree of affiliation between the user and each person is based at least in part on a group assigned to each person by the user.
6. The method of claim 1 , wherein determining the degree of affiliation between the user and each person is based at least in part on a number of images having both the user and each person.
7. The method of claim 1 wherein determining the degree of affiliation between the user and each person is based at least in part on a number of postings between the user and each person.
8. The method of claim 1 wherein determining the degree of affiliation between the user and each person is based at least in part on a number of direct interactions between the user and each person.
9. A system to crop an image including one or more processors, the system comprising:
a face detector that detects one or more faces within an image;
a search system that evaluates the one or more faces to identify a subset of faces each corresponding to a person within a user's online social network;
a saliency analyzer that determines a degree of affiliation between the user and each person in the subset of the faces within the user's online social network, determines saliency values of pixels within the image, and adjusts the saliency values of pixels within the image based on the determined degree of affiliation; and
a cropping system that crops the image based on the adjusted saliency values.
10. The system of claim 9 , wherein the saliency analyzer also defines a first crop region including the subset of the one or more faces based on the adjusted saliency values.
11. The system of claim 10 , wherein the crop region is defined to exclude faces that correspond to persons not within the user's online social network.
12. The system of claim 10 , wherein the cropping system crops the image based on the first crop region.
13. The system of claim 9 , wherein the saliency analyzer determines the degree of affiliation between the user and each person based at least in part on a group assigned each person by the user.
14. The system of claim 9 , wherein the saliency analyzer determines the degree of affiliation between the user and each person based at least in part on a number of images having both the user and each person.
15. The system of claim 9 wherein the saliency analyzer determines the degree of affiliation between the user and each person based at least in part on a number of postings between the user and each person.
16. The system of claim 9 wherein the saliency analyzer determines the degree of affiliation between the user and each person based at least in part on a number of direct interactions between the user and each person.
17. A non-transitory computer-readable medium with an executable program stored thereon, wherein the program when executed instructs a processor to perform operations comprising:
detecting one or more faces within an image;
evaluating the one or more faces to identify a subset of faces each corresponding to a person within a user's online social network;
determining a degree of affiliation between the user and each person in the subset of the faces within the user's online social network;
determining saliency values of pixels within the image;
adjusting the saliency values of pixels within the image based on the determined degree of affiliation; and
cropping the image based on the adjusted saliency values.
18. The computer-readable medium of claim 17 , wherein the operations further comprise defining a first crop region including the subset of the one or more faces based on the adjusted saliency values.
19. The computer-readable medium of claim 18 , wherein the crop region is defined to correspond to persons not within the user's online social network.
20. The computer-readable medium of claim 18 , wherein the image is cropped based on the first crop region.