Identifying video content via fingerprint matching

摘要

Methods and systems to identify video content based on video fingerprint matching are described. In some example embodiments, the methods and systems generate a query fingerprint of a frame of video content captured at a client device, query a database of reference fingerprints, determine the query fingerprint of the frame of captured video content matches a reference fingerprint, and identify the video content based on the match of fingerprints.

主权项

1. A computer-implemented method, comprising:
accessing a query fingerprint of a single video frame of video content captured at a client device, the query fingerprint being generated based on a first value of a first spatial region within the single video frame of video content, the first value of the first spatial region being calculated by subtracting a spatial sub-region of the first spatial region from one or more other spatial sub-regions of the first spatial region; querying a database of reference fingerprints associated with video frames of known video content, each of the reference fingerprints being generated based on spatial regions within a different single video frame of the known video content; determining that the query fingerprint matches at least one of the reference fingerprints; and identifying the video content captured at the client device based on the determination that the query fingerprint matches at least one of the reference fingerprints.