Back to results
US 10,474,899 B2Granted
Social engagement based on image resemblance
AssigneeFacebook, Inc.
InventorShivani Jalan
Life of this patent
Estimating the term…
Abstract
The present disclosure is directed toward systems and methods for identifying and providing a user of a networking system with other users of the networking system that have a facial resemblance to the user (e.g., look-alike users). In particular, a facial resemblance system uses an image of a user to identify other users that have a facial resemblance to the user (e.g., look-alike users). The facial resemblance system can present look-alike users to the user based on a resemblance score and/or a commonality score. Further, the facial resemblance system can employ feedback from users to improve the accuracy of the facial resemblance system. Upon receiving one or more look-alike users, the user can then engage (e.g., communicate or socially connect) with one or more of the look-alike users.
Claims20
A method comprising:
- storing a plurality of images of users of a networking system in an image database;
- determining facial features of one or more users of the networking system in each image of the plurality of images, the facial features comprising high-level facial features and lower-level facial features;
- generating, for each image of the plurality of images, a facial attribute data vector based on the determined facial features, wherein each facial attribute data vector comprises a first vector portion corresponding to the high-level facial features and a second vector portion corresponding to the lower-level facial features;
- identifying a first image of a first user of the networking system;
- determining a first facial attribute data vector for the first image, the first facial attribute data vector comprising a high-level portion corresponding to high-level facial features of the first user and a lower-level portion corresponding to lower-level facial features of the first user;
- identifying, from the plurality of images, a subset of images by:
- comparing the first vector portions from the facial attribute data vectors of the plurality of images to the high-level portion of the first facial attribute data vector of the first image;
- and
- excluding images from the plurality of images not sharing one or more high-level facial features with the first image based on the comparing;
- determining, by at least one processor and from the identified subset of images, one or more images comprising one or more other users of the networking system having a facial resemblance to the first user by comparing the second vector portions from the facial attribute data vectors of the identified subset of images to the lower-level portion from the first facial attribute data vector of the first image;
- and
- providing, to the first user and via the networking system, one or more options for engaging with the one or more other users of the networking system having a facial resemblance to the first user.
9 more elements
A system comprising:
- at least one processor;
- and
- at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:
- store a plurality of images of users of a networking system in an image database;
- determine facial features of one or more users of the networking system in each image of the plurality of images, the facial features comprising high-level facial features and lower-level facial features;
- generate, for each image of the plurality of images, a facial attribute data vector based on the determined facial features, wherein each facial attribute data vector comprises a first vector portion corresponding to the high-level facial features and a second vector portion corresponding to the lower-level facial features;
- identify a first image of a first user of the networking system;
- determine a first facial attribute data vector for the first image, the first facial attribute data vector comprising a high-level portion corresponding to high-level facial features of the first user and a lower-level portion corresponding to lower-level facial features of the first user;
- identify, from the plurality of images, a subset of images by:
- compare the first vector portions from the facial attribute data vectors of the plurality of images to the high-level portion of the first facial attribute data vector of the first image;
- and
- exclude images from the plurality of images not sharing one or more high-level facial features with the first image based on the comparing;
- determine, by at least one processor and from the identified subset of images, one or more images comprising one or more other users of the networking system having a facial resemblance to the first user by comparing the second vector portions from the facial attribute data vectors of the identified subset of images to the lower-level portion from the first facial attribute data vector of the first image;
- and
- provide, to the first user and via the networking system, one or more options for engaging with the one or more other users of the networking system having a facial resemblance to the first user.
12 more elements
A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computer system to:
- store a plurality of images of users of a networking system in an image database;
- determine facial features of one or more users of the networking system in each image of the plurality of images, the facial features comprising high-level facial features and lower-level facial features;
- generate, for each image of the plurality of images, a facial attribute data vector based on the determined facial features, wherein each facial attribute data vector comprises a first vector portion corresponding to the high-level facial features and a second vector portion corresponding to the lower-level facial features;
- identify a first image of a first user of the networking system;
- determine a first facial attribute data vector for the first image, the first facial attribute data vector comprising a high-level portion corresponding to high-level facial features of the first user and a lower-level portion corresponding to lower-level facial features of the first user;
- identify, from the plurality of images, a subset of images by:
- compare the first vector portions from the facial attribute data vectors of the plurality of images to the high-level portion of the first facial attribute data vector of the first image;
- and
- exclude images from the plurality of images not sharing one or more high-level facial features with the first image based on the comparing;
- determine, by at least one processor and from the identified subset of images, one or more images comprising one or more other users of the networking system having a facial resemblance to the first user by comparing the second vector portions from the facial attribute data vectors of the identified subset of images to the lower-level portion from the first facial attribute data vector of the first image;
- and
- provide, to the first user and via the networking system, one or more options for engaging with the one or more other users of the networking system having a facial resemblance to the first user.
9 more elements
Dependencies are inferred from the claim text.