Tagging Personal Photos with Deep Networks

摘要

Techniques and constructs to facilitate automatic tagging can provide improvements in image storage and searching. The constructs may enable training a deep network using tagged source images and target images. The constructs may also train a top layer of the deep network using a personal photo ontology. The constructs also may select one or more concepts from the ontology for tagging personal digital images.

主权项

1. A method comprising:
providing an ontology for personal digital images, the ontology comprising a hierarchy including a plurality of concepts grouped into a plurality of nodes of the hierarchy, each of the plurality of concepts comprising a textual descriptor for association with one or more personal digital images; providing a plurality of source digital images from a source domain, each of the source digital images having at least one associated textual descriptor; providing a plurality of target digital images from a target domain; training, on a computing device, a deep network using the source digital images, the target digital images, and the ontology; receiving, at the computing device, one or more personal digital images; applying, using the computing device, the deep network to the one or more personal digital images to determine one or more of the concepts for association with each of the one or more personal digital images; and associating at least one of the one or more of the concepts to each of the one or more personal digital images.