Identifying media content via fingerprint matching
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.
1. A method comprising:
generating, by one or more processors of a client device, a query fingerprint based on a subtraction of a spatial subregion within a spatial region of a query media frame from at least one other spatial subregion of the spatial region of the query media frame, wherein the query media frame is a video frame within video content received by the client device, wherein the client device comprises a display configured to display the video content, wherein a pillar bar is identified in the spatial region and the identified pillar bar is excluded from the spatial region prior to generating the query fingerprint;
comparing, by one or more processors of the client device, the query fingerprint to a reference fingerprint generated based on a subtraction of a spatial subregion within a spatial region of a reference media frame from at least one other spatial subregion of the spatial region of the reference media frame;
determining, by one or more processors of the client device, that the query fingerprint matches the reference fingerprint; and
identifying, by one or more processors of the client device, the video content based on the determining that the query fingerprint matches the reference fingerprint.
2. The method of claim 1 , wherein:
the subtraction of the spatial subregion from at least one other spatial subregion of the spatial region of the query media frame includes a subtraction of an inner subregion of the spatial region from at least one outer region of the spatial region of the query media frame.
3. The method of claim 1 , wherein:
of the pillar bar is identified by performing a binary search for an edge of the spatial region of the query media frame.
4. The method of claim 1 , wherein:
the spatial subregion is a first spatial subregion within a first spatial region of the query media frame; and
the query fingerprint is generated based further on a subtraction of a second spatial subregion within a second spatial region of the query media frame from at least one other spatial subregion of the second spatial region of the query media frame.
5. The method of claim 4 , wherein:
the second spatial region of the query media frame overlaps the first spatial region of the query media frame.
6. The method of claim 4 , wherein:
the second spatial region of the query media frame coincides with the first spatial region of the query media frame.
7. The method of claim 4 , wherein:
the second spatial region of the query media frame is oriented perpendicular to the first spatial region of the query media frame.
8. The method of claim 4 , wherein:
the second spatial subregion within the second spatial region of the query media frame is oriented perpendicular to the first spatial subregion within the first spatial region of the query media frame.
9. The method of claim 4 , wherein:
the first and second spatial regions of the query media frame have different first and second spatial sizes; and
the query fingerprint is generated based further on different first and second weight values that represent the different first and second spatial sizes of the first and second spatial regions of the query media frame.
10. The method of claim 1 , further comprising:
providing an identifier associated with the video content.
11. The method of claim 1 , further comprising:
querying a database of reference fingerprints.
12. The method of claim 10 , further comprising:
accessing, by the client device, supplemental content associated with the video content based on the identifier.
13. 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:
generating a query fingerprint based on a subtraction of a spatial subregion within a spatial region of a query media frame from at least one other spatial subregion of the spatial region of the query media frame, wherein the query media frame is a video frame within video content received by the client device, wherein the client device comprises a display configured to display the video content, wherein a pillar bar is identified in the spatial region and the identified pillar bar is excluded from the spatial region prior to generating the query fingerprint;
comparing the query fingerprint to a reference fingerprint generated based on a subtraction of a spatial subregion within a spatial region of a reference media frame from at least one other spatial subregion of the spatial region of the reference media frame;
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.
14. The non-transitory machine-readable storage medium of claim 13 , wherein:
the subtraction of the spatial subregion from at least one other spatial subregion of the spatial region of the query media frame includes a subtraction of an inner subregion of the spatial region from at least one outer region of the spatial region of the query media frame.
15. The non-transitory machine-readable storage medium of claim 13 , wherein:
the spatial subregion is a first spatial subregion within a first spatial region of the query media frame; and
the query fingerprint is generated based further on a subtraction of a second spatial subregion within a second spatial region of the query media frame from at least one other spatial subregion of the second spatial region of the query media frame.
16. A system comprising:
a display;
one or more processors; 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:
generating a query fingerprint based on a subtraction of a spatial subregion within a spatial region of a query media frame from at least one other spatial subregion of the spatial region of the query media frame, wherein the query media frame is a video frame within video content received by the system, wherein the display is configured to display the video content, wherein a pillar bar is identified in the spatial region and the identified pillar bar is excluded from the spatial region prior to generating the query fingerprint;
comparing the query fingerprint to a reference fingerprint generated based on a subtraction of a spatial subregion within a spatial region of a reference media frame from at least one other spatial subregion of the spatial region of the reference media frame;
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.
17. The system of claim 16 , wherein:
the subtraction of the spatial subregion from at least one other spatial subregion of the spatial region of the query media frame includes a subtraction of an inner subregion of the spatial region from at least one outer region of the spatial region of the query media frame.
18. The system of claim 16 , wherein:
the spatial subregion is a first spatial subregion within a first spatial region of the query media frame; and
the query fingerprint is generated based further on a subtraction of a second spatial subregion within a second spatial region of the query media frame from at least one other spatial subregion of the second spatial region of the query media frame.
19. The system of claim 18 , wherein:
the first and second spatial regions of the query media frame are rectangular; and
the rectangular second spatial region of the query media frame is oriented perpendicular to the rectangular first spatial region of the query media frame.