Identifying video content via fingerprint matching
AssigneeRoku, Inc.
InventorWilson Harron
Life of this patent
Estimating the term…
Abstract
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.
Claims20
A method for a client device comprising:
- selecting a plurality of patches of at least one video frame of video content received by the client device;
- calculating for each respective patch of the plurality of patches, a respective value by subtracting a middle region of the respective patch from outer regions of the respective patch, to obtain a plurality of values;
- generating a query fingerprint based on the plurality of values;
- comparing the query fingerprint to a reference fingerprint;
- determining that the query fingerprint matches the reference fingerprint;
- and
- identifying the video content based on the determining that the query fingerprint matches the reference fingerprint.
A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a client device, cause the client device to perform operations comprising:
- selecting a plurality of patches of at least one video frame of video content received by the client device;
- calculating, for each respective patch of the plurality of patches, a respective value by subtracting a middle region of the respective patch from outer regions of the respective patch, to obtain a plurality of values;
- generating a query fingerprint based on the plurality of values;
- comparing the query fingerprint to a reference fingerprint;
- determining that the query fingerprint matches the reference fingerprint;
- and
- identifying the video content based on the determining that the query fingerprint matches the reference fingerprint.
A system comprising:
- a display;
- one or more processors communicatively coupled to the display;
- and
- a memory storing instructions that, when executed by at least one processor among the one or more processors, cause the system to perform operations comprising:
- selecting a plurality of patches of at least one video frame of video content;
- calculating, for each respective patch of the plurality of patches, a respective value by subtracting a middle region of the respective patch from outer regions of the respective patch, to obtain a plurality of values;
- generating a query fingerprint based on the plurality of values;
- comparing the query fingerprint to a reference fingerprint;
- determining that the query fingerprint matches the reference fingerprint;
- and
- identifying the video content based on the determining that the query fingerprint matches the reference fingerprint.
Dependencies are inferred from the claim text.