US 8,861,804 B1Granted

Assisted photo-tagging with facial recognition models

AssigneeShutterfly, Inc.

InventorsAndrea R. Johnson, Matthew J. Johnson, Nico Toutenhoofd, Clinton L. Fenton

Life of this patent

Estimating the term…

Loading patent…

Abstract

Embodiments of the invention perform assisted tagging of images, including tagging of people, locations, and activities depicted in those images. A batch of images is received comprising images of faces, including at least some faces that have not yet been tagged. A facial recognition algorithm is applied to the faces to determine matching data comprising possible tags for each untagged face. A logic engine applies logic rules to reduce the likelihood that certain matches are correct. The most likely match from among the possible matches is selected for suggestion to the user for verification. Once verified, the metadata of the image indicating the recognized people within the image is updated.

Claims20

Dependent claims

A computer-implemented method for tagging images, comprising:

receiving a batch of images comprising images of faces;
identifying a portion of an image in the batch that corresponds to an untagged face;
applying a facial recognition algorithm to the portion of the image, wherein the facial recognition algorithm takes input from a plurality of facial recognition models, wherein the plurality of facial recognition models each is associated with a known person;
receiving, from the facial recognition algorithm, matching data comprising possible tags for the untagged face, wherein each of the possible tags for the untagged face is associated with one of the known persons and a probability factor;
determining by a computer system, based on logic rules a likelihood for one of the possible tags to correctly match the untagged face, wherein the step of determining comprises:
identifying a highest probability factor among probability factors associated with known persons for multiple untagged faces;
assigning a first untagged face to a first known person based on the highest probability factor;
and
eliminating at least one of the possible tags from a second untagged face based on the highest probability factor;
and
automatically selecting, by the computer system, a provisional tag for the untagged face from the possible tags based on the likelihood.

8 more elements

Dependencies are inferred from the claim text.