Automatic suggestion to share images
Some implementations can include a computer-implemented method and/or system for automatic suggestion to share images. The method can include identifying a plurality of images associated with a user and detecting one or more entities in the plurality of images. The method can also include constructing an aggregate feature vector for the plurality of images based on the one or more entities in the plurality of images and determining that the aggregate feature vector matches a first cluster. The method can further include, in response to determining that the aggregate feature vector matches the first cluster, providing a suggestion to the user for an image composition based on the plurality of images.
1. A computer-implemented method comprising:
identifying images associated with a user;
detecting one or more entities in the images;
constructing an aggregate feature vector for the images that describes a number of each type of entity in the images;
performing a vector comparison of the aggregate feature vector to cluster features to identify similarities; and
generating an image composition from the images wherein the image composition includes one or more images with features associated with a likelihood of sharing that meets a threshold, wherein the likelihood of sharing is determined based on the vector comparison.
2. The method of claim 1 , further comprising:
generating groups of images based on the clustered features, wherein at least one of the groups of images includes a type of activity not associated with prior groups of images; and
providing a suggestion to the user for a new group based on the type of activity not associated with prior groups of images.
3. The method of claim 2 , further comprising determining a match between the aggregate feature vector and a first cluster with a first cluster feature based on the aggregate feature vector meeting a first cluster-specific threshold for the first cluster.
4. The method of claim 3 , wherein the first cluster-specific threshold indicates that an entity is present in at least a percentage of respective images from the first cluster.
5. The method of claim 3 , further comprising providing a suggestion in a user interface to share an image from the first cluster responsive to a determination that the image meets one or more quality criteria.
6. The method of claim 1 , wherein performing the vector comparison includes determining a vector distance between the aggregate feature vector and different cluster vectors that includes respective cluster features.
7. The method of claim 1 , further comprising normalizing the aggregate feature vector by multiplying the aggregate feature vector by a scaling factor that represents a total number of the images associated with the user.
8. The method of claim 1 , wherein the type of entity includes at least one of an animal type, a food type, or a person type in the images.
9. A non-transitory computer-readable medium with instructions stored thereon that, when executed by one or more computers, cause the one or more computers to perform operations, the operations comprising:
identifying images associated with a user;
detecting one or more entities in the images;
constructing an aggregate feature vector for the images that describes a number of each type of entity in the images;
performing a vector comparison of the aggregate feature vector to cluster features to identify similarities; and
generating an image composition from the images wherein the image composition includes one or more images with features associated with a likelihood of sharing that meets a threshold, wherein the likelihood of sharing is determined based on the vector comparison.
10. The computer-readable medium of claim 9 , wherein the operations further comprise:
generating groups of images based on the clustered features, wherein at least one of the groups of images includes a type of activity not associated with prior groups of images; and
providing a suggestion to the user for a new group based on the type of activity not associated with prior groups of images.
11. The computer-readable medium of claim 10 , wherein the operations further comprise determining a match between the aggregate feature vector and a first cluster with a first cluster feature based on the aggregate feature vector meeting a first cluster-specific threshold for the first cluster.
12. The computer-readable medium of claim 11 , wherein the first cluster-specific threshold indicates that an entity is present in at least a percentage of respective images from the first cluster.
13. The computer-readable medium of claim 11 , wherein the operations further comprise providing a suggestion in a user interface to share an image from the first cluster responsive to a determination that the image meets one or more quality criteria.
14. The computer-readable medium of claim 9 , wherein performing the vector comparison includes determining a vector distance between the aggregate feature vector and different cluster vectors that includes respective cluster features.
15. A system comprising:
one or more processors; and
a memory that stores instructions that, when executed by the one or more processors cause the one or more processors to perform operations comprising:
identifying images associated with a user;
detecting one or more entities in the images;
constructing an aggregate feature vector for the images that describes a number of each type of entity in the images;
performing a vector comparison of the aggregate feature vector to cluster features to identify similarities; and
generating an image composition from the images wherein the image composition includes one or more images with features associated with a likelihood of sharing that meets a threshold, wherein the likelihood of sharing is determined based on the vector comparison.
16. The system of claim 15 , wherein the operations further comprise:
generating groups of images based on the clustered features, wherein at least one of the groups of images includes a type of activity not associated with prior groups of images; and
providing a suggestion to the user for a new group based on the type of activity not associated with prior groups of images.
17. The system of claim 16 , wherein the operations further comprise determining a match between the aggregate feature vector and a first cluster with a first cluster feature based on the aggregate feature vector meeting a first cluster-specific threshold for the first cluster.
18. The system of claim 17 , wherein the first cluster-specific threshold indicates that an entity is present in at least a percentage of respective images from the first cluster.
19. The system of claim 17 , wherein the operations further comprise providing a suggestion in a user interface to share an image from the first cluster responsive to a determination that the image meets one or more quality criteria.
20. The system of claim 15 , wherein performing the vector comparison includes determining a vector distance between the aggregate feature vector and different cluster vectors that includes respective cluster features.