Content tagging using broadcast device information
First Claim
1. A computer-implemented method, comprising:
- on a first device, receiving information from a plurality of second devices located within a communication range of the first device, the information comprising a plurality of identifiers, each identifier associated with one of the second devices;
identifying a plurality of candidate labels, each candidate label associated with at least one of the identifiers;
creating an image file on the first device by recording a plurality of images using a camera comprised within the first device, the plurality of images comprising at least one image of a user of at least one of the plurality of second devices;
assigning an identification probability to each of a plurality of candidate subjects identified in a subject database, wherein the identification probability assigned to each candidate subject represents a probability that the at least one image of the user comprises an image of the respective candidate subject, based on a facial recognition algorithm comparing at least a portion of the image file with the respective candidate subject;
comparing at least a subset of the plurality of candidate subjects with each of the plurality of candidate labels;
adjusting the identification probability of each of the compared candidate subjects, based on the comparing; and
associating at least one of the compared candidate subjects with the image file, using the adjusted identification probability.
0 Assignments
0 Petitions
Accused Products
Abstract
A number of devices co-located at a geographic location can broadcast and receive identity information. The identity information can include a unique device identifier and a device description. The identity information can be exchanged between various electronic devices using a communication link having limited transmission range. Device identifiers and corresponding device descriptions included in the tokens can be associated with content on the device receiving the tokens. The device descriptions can be used as hints for assigning labels to the devices identified by device identifiers. The labels can be associated with the content. The labeled content can be classified, organized, indexed and searched based at least in part on the labels.
-
Citations
18 Claims
-
1. A computer-implemented method, comprising:
-
on a first device, receiving information from a plurality of second devices located within a communication range of the first device, the information comprising a plurality of identifiers, each identifier associated with one of the second devices; identifying a plurality of candidate labels, each candidate label associated with at least one of the identifiers; creating an image file on the first device by recording a plurality of images using a camera comprised within the first device, the plurality of images comprising at least one image of a user of at least one of the plurality of second devices; assigning an identification probability to each of a plurality of candidate subjects identified in a subject database, wherein the identification probability assigned to each candidate subject represents a probability that the at least one image of the user comprises an image of the respective candidate subject, based on a facial recognition algorithm comparing at least a portion of the image file with the respective candidate subject; comparing at least a subset of the plurality of candidate subjects with each of the plurality of candidate labels; adjusting the identification probability of each of the compared candidate subjects, based on the comparing; and associating at least one of the compared candidate subjects with the image file, using the adjusted identification probability. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A non-transitory computer-readable medium having instructions stored thereon, which, when executed by at least one processor of a first device, cause the first device to:
-
receive information from a plurality of second devices located within a communication range of the first device, the information comprising a plurality of identifiers, each identifier associated with one of the second devices; identify a plurality of candidate labels, each candidate label associated with at least one of the identifiers; create an image file by recording a plurality of images using a camera comprised within the first device, the plurality of images comprising at least one image of a user of at least one of the plurality of second devices; assign an identification probability to each of a plurality of candidate subjects identified in a subject database, wherein the identification probability assigned to each candidate subject represents a probability that the at least one image of the user comprises an image of the respective candidate subject, based on a facial recognition algorithm comparing at least a portion of the image file with the respective candidate subject; compare at least a subset of the plurality of candidate subjects with each of the plurality of candidate labels; adjust the identification probability of each of the compared candidate subjects, based on the comparing; and associate at least one of the compared candidate subjects with the image file, using the adjusted identification probability. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A mobile wireless electronic device, comprising:
-
wireless communication circuitry; a camera; and at least one processor coupled to the wireless communication circuitry and the camera, the at least one processor configured to cause the mobile wireless electronic device to; receive, via the wireless communication circuitry, information from a plurality of second devices located within a communication range of the mobile wireless electronic device, the information comprising a plurality of identifiers, each identifier associated with one of the second devices identify a plurality of candidate labels, each candidate label associated with at least one of the identifiers; create an image file by recording a plurality of images using the camera, the plurality of images comprising at least one image of a user of at least one of the plurality of second devices; assign an identification probability to each of a plurality of candidate subjects identified in a subject database, wherein the identification probability assigned to each candidate subject represents a probability that the at least one image of the user comprises an image of the respective candidate subject, based on a facial recognition algorithm comparing at least a portion of the image file with the respective candidate subject; compare at least a subset of the plurality of candidate subjects with each of the plurality of candidate labels; adjust the identification probability of each of the compared candidate subjects, based on the comparing; and associate at least one of the compared candidate subjects with the image file, using the adjusted identification probability. - View Dependent Claims (14, 15, 16, 17, 18)
-
Specification