Identification of unknown altered versions of a known base media item
Small changes in a broadcast version of a base media item can be identified by performing a multi-level comparison of digital fingerprints. A fingerprint of a base media item is compared to a fingerprint of a media broadcast to determine whether a media item embedded in a broadcast is likely, to a first level of certainty, to be the base media item. A second, more stringent, match between the fingerprint of the base media item and loosely matched items can be used to identify potentially-altered versions of the base media item. Potentially-altered versions can be compared against each other, and resulting matches are flagged as altered base media items, which can be fingerprinted and tested against broadcast fingerprints in the same manner as the base media item. Comparisons are made in parallel between two fingerprints to distinguish between a known base media item and unknown altered versions of the known base media item without prior storage of the unknown altered versions of the known base media item.
1. A method for use in a computing device implementing an identification server, the method comprising:
obtaining, at the identification server, first representations of broadcast content broadcast by a plurality of different media stations;
storing each of the first representations of broadcast content in separate buffers as buffered representations, wherein particular separate buffers are associated with particular media stations of the plurality of different media stations;
receiving, at the identification server, a second representation of media content captured by an end user device;
performing comparisons in parallel between the second representation of media content and each of a plurality of the buffered representations to distinguish between a known base media item and unknown altered versions of the known base media item; and
wherein the comparison of the first representations of broadcast content and the second representation of media content is performed without prior storage of the unknown altered versions of the known base media item by the identification server.
2. The method of claim 1 , wherein the broadcast content and the media content include live broadcasts.
3. The method of claim 1 , wherein the broadcast content and the media content are received during a substantially same time period.
4. The method of claim 1 , wherein the broadcast content and the media content are received during a substantially same time period, but compared during a delayed time period.
5. The method of claim 1 , wherein the buffered representations each include a substantially continuous fingerprint of broadcast content over a limited time duration.
6. The method of claim 5 , further comprises appending newer-in-time portions of substantially continuous fingerprints to the particular separate buffers.
7. The method of claim 6 , further comprises limiting a size of the substantially continuous fingerprints by flushing older-in-time portions of the substantially continuous fingerprints from the particular separate buffers as newer-in-time portions of the substantially continuous fingerprints are appended.
8. The method of claim 1 , wherein the performing comparisons includes performing a series of successively stricter comparisons between the second representation of media content and each of the buffered representations.
9. The method of claim 1 , further comprises accumulating the buffered representations in parallel.
10. A device implementing an identification server, the device comprises:
a processor;
a memory coupled to the processor; the memory configured to implement a plurality of buffers;
a processor configured to:
obtain, at the identification server, first representations of broadcast content broadcast by a plurality of different media stations;
store each of the first representations of broadcast content in separate buffers as buffered representations, wherein particular separate buffers are associated with particular media stations of the plurality of different media stations;
receive, at the identification server, a second representation of media content captured by an end user device;
perform comparisons in parallel between the second representation of media content and each of a plurality of the buffered representations to distinguish between a known base media item and unknown altered versions of the known base media item; and
wherein the comparison of the first representations of broadcast content and the second representation of media content is performed without prior storage of the unknown altered versions of the known base media item by the identification server.
11. The device of claim 10 , wherein the broadcast content and the media content include live broadcasts.
12. The device of claim 10 , wherein the broadcast content and the media content are received during a substantially same time period.
13. The device of claim 10 , wherein the broadcast content and the media content are received during substantially same time period, but compared during a delayed time period.
14. The device of claim 10 , wherein the buffered representations each include a substantially continuous fingerprint of broadcast content over a limited time duration.
15. The device of claim 14 , further comprises appending newer-in-time portions of substantially continuous fingerprints to the particular separate buffers.
16. The device of claim 10 , wherein the performing comparisons includes performing a series of successively stricter comparisons between the second representation of media content and each of the buffered representations.
17. The device of claim 10 , further comprises accumulating the buffered representations in parallel.
18. A non-transitory computer readable medium tangibly embodying a program of computer executable instructions, the program of computer executable instructions including:
at least one instruction to obtain first representations of broadcast content broadcast by a plurality of different media stations;
at least one instruction to store each of the first representations of broadcast content as buffered representations in separate buffers of a memory, wherein particular separate buffers are associated with particular media stations of the plurality of different media stations;
at least one instruction to receive a second representation of media content captured by an end user device;
at least one instruction to perform comparisons in parallel between the second representation of media content and each of a plurality of the buffered representations to distinguish between a known base media item and unknown altered versions of the known base media item; and
wherein the comparison of the first representations of broadcast content and the second representation of media content is performed without prior storage of the unknown altered versions of the known base media item.
19. The non-transitory computer readable medium of claim 18 , wherein the broadcast content and the media content are received during a substantially same time period.
20. The non-transitory computer readable medium of claim 18 , wherein the broadcast content and the media content are received during substantially same time period, but compared during a delayed time period.