Back to results
US 10,853,690 B2Granted
Method and system for attaching a metatag to a digital image
AssigneeAvigilon Patent Holding 1 Corporation
InventorsAlex Shah, Charles A. Myers
Life of this patent
Estimating the term…
Abstract
A system and method for tagging an image of an individual in a plurality of photos is disclosed herein. A feature vector of an individual is used to analyze a set of photos on a social networking website such as Facebook® to determine if an image of the individual is present in a photo of the set of photos. Photos having an image of the individual are tagged preferably by listing a URL or URI for each of the photos in a database.
Claims20
A system for identifying an individual, the system comprising:
- a server configured to receive a first set of one or more photos from a computing device, the first set of one or more photos including at least one photo containing a facial image of an individual;
- and
- a database accessible to the server including a second set of two or more photos corresponding to a plurality of existing feature vectors of images of target individuals depicted in the second set of two or more photos,
- wherein the server is configured to process the first set of one or more photos to generate a feature vector for the facial image of the individual;
- wherein the server is configured to compare the generated feature vector to the plurality of existing feature vectors to find an existing feature vector of an image of a target individual that most closely matches the generated feature vector;
- wherein the server, based on the closest match, is configured to identify each photo among the second set of two or more photos in which the image of the target individual is present;
- wherein the server is configured to create a third set of two or more photos that includes the at least one photo containing the facial image of the individual and each photo among the second set of two or more photos in which the image of the target individual is present;
- and
- wherein the server is configured to send the third set of two or more photos to the computing device.
6 more elements
A method for identifying an individual, the method comprising:
- receiving, at a server, a first set of one or more photos from a computing device, the first set of one or more photos including at least one photo containing a facial image of an individual;
- accessing, by the server, a database that includes a second set of two or more photos corresponding to a plurality of existing feature vectors of images of target individuals depicted in the second set of two or more photos;
- processing, at the server, the first set of one or more photos to generate a feature vector for the facial image of the individual;
- comparing, at the server, the generated feature vector to the plurality of existing feature vectors to find an existing feature vector of an image of a target individual that most closely matches the generated feature vector;
- identifying based on the closest match, at the server, each photo among the second set of two or more photos in which the image of the target individual is present;
- creating, at the server, a third set of two or more photos that includes the at least one photo containing the facial image of the individual and each photo among the second set of two or more photos in which the image of the target individual is present;
- and
- sending, at the server, the third set of two or more photos to the computing device.
5 more elements
A computer readable medium having stored thereon instructions that when executed by a processor cause the processor to identify an individual in a photo, the instructions comprising instructions to:
- receive, at a server, a first set of one or more photos from a computing device, the first set of two or more photos including at least one photo containing a facial image of an individual;
- access, by the server, a database that includes a second set of plurality of photos corresponding to a plurality of existing feature vectors of images of target individuals depicted in the second set of two or more photos;
- process, at the server, the first set of two or more photos to generate a feature vector for the facial image of the individual;
- compare, at the server, the generated feature vector to the plurality of existing feature vectors to find an existing feature vector of an image of a target individual that most closely matches the generated feature vector;
- identify based on the closest match, at the server, each photo among the second set of two or more photos in which the image of the target individual is present;
- create, at the server, a third set of two or more photos that includes the at least one photo containing the facial image of the individual and each photo among the second set of two or more photos in which the image of the target individual is present;
- and
- send, at the server, the third set of two or more photos to the computing device.
5 more elements
Dependencies are inferred from the claim text.