VIDEO IMAGE SEARCH

摘要

Techniques disclosed herein provide for conducting an image search of video frames using a captured image of a display or a screen capture of a media item during playback. Results of the image search may be used to play back a corresponding video from the point in the video at which the captured image was taken, initiate a second-screen user experience, and/or perform other functions. Techniques are also disclosed for building a library of video frames with which image searches may be conducted.

主权项

1. A method of conducting a video image search and providing results thereof, the method comprising:
receiving, via a data communications network interface, an image; extracting one or more of features of the image; generating a representation of the image, based on the one or more features; comparing, using a processing unit, the generated representation with a plurality of stored representations, wherein the plurality of stored representations includes stored representations of video frames from one or more videos; determining a subset of the plurality of stored representations, the subset comprising stored representations with a degree of similarity to the generated representation above a certain threshold; and sending, via the data communications network interface, information regarding the subset of the plurality of stored representations, wherein the information comprises, for each stored representation in the subset, a Universal Resource Locator (URL) related to a video corresponding to the stored representation.