Methods, Apparatus and Programs for Generating and Utilizing Content Signatures

• US 20070101147A1
• Filed: 12/20/2006
• Published: 05/03/2007
• Est. Priority Date: 12/21/2000
• Status: Active Grant

• Current Assignee: Digimarc Corporation
• Original Assignee: Digimarc Corporation
• Inventors: Brunk, Hugh, Levy, Kenneth
• Granted Patent: US 8,023,773 B2
• Time in Patent Office: Days
• US Class Current: 713/176
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: H04N 19/467 characterised by the embedded information being invisible, e.g. watermarking
• CPC Class Codes: H04N 19/48 using compressed domain processing techniques other than decoding, e.g. modification of transform coefficients, variable length coding [VLC] data or run-length data motion estimation in a transform domain H04N19/547; processing of decoded motion vectors H04N19/513

Abstract

The present invention generally relates to deriving and/or utilizing content signatures. A content signature includes a representation of a content item, which is derived from the content item itself. According to one embodiment of the invention, a method includes: obtaining a content item; transforming the content item to obtain transform domain coefficients; applying Viterbi decoding to at least a set of the transform domain coefficients; using at least one result of the Viterbi decoding as a content signature for the content item. Other embodiments are provided and claimed as well.

Claims

1. A method comprising:

obtaining a content item comprising a plurality of frames or segments;

obtaining a key;

seeding a pseudo-random generator with the key to select a set of the plurality of frames or segments;

deriving a content signature for the content item from data within the set of the plurality of frames or segments, the content signature comprising a reduced-bit representation of the set of the plurality of frames or segments.

2. The method of claim 1 wherein the content signature comprises a unique identifier of the content item.

3. The method of claim 1 wherein the content item comprises video.

4. The method of claim 3 wherein the video comprises compressed video.

5. The method of claim 1 wherein the content item comprise audio.

6. The method of claim 5 wherein the audio comprises compressed audio.

7. A machine-readable medium comprising instructions stored thereon to perform the method of claim 1.

8. A method comprising:

obtaining a content item;

transforming the content item to obtain transform domain coefficients;

applying Viterbi decoding to at least a set of the transform domain coefficients; and

using at least one result of the Viterbi decoding as a content signature representing the content item.

9. The method of claim 8 wherein the act of transforming utilizes a wavelet transformation.

10. The method of claim 9 wherein the set of the transform domain coefficients corresponds to low frequency coefficients.

11. A method of claim 8 wherein the content signature comprises a reduced-bit representation of the content item.

12. A machine-readable medium comprising instructions stored thereon to perform the method of claim 8.

13. A machine-readable medium comprising instructions stored thereon to perform the method of claim 9.

14. A method comprising:

obtaining a content item, the content item including auxiliary data steganographically embedded therein;

decoding the auxiliary data steganographically embedded within the content item;

dynamically deriving a content signature from the content item, the content signature comprising a reduced-bit representation of the content item; and

carrying out an action as dictated by the auxiliary data, the action involving the content signature.

15. The method of claim 14 wherein the content item comprises video or audio.

16. The method of claim 14 wherein the action comprises forwarding the content signature to a remote database.

17. The method of claim 14 wherein the action comprise storing the content signature in a local repository.

18. A method comprising:

obtaining a content item;

dynamically deriving a first content signature from the content item, the first content signature comprising a first reduced-bit representation of the content item;

dynamically deriving a second content signature from the content item, the second content signature comprising a second reduced-bit representation of the content item;

providing the first content signature to narrow identification of the content item or metadata associated with the content item to a set of content items or metadata; and

providing the second content signature to further narrow identification of the content item or metadata associated with the content item within the set of content items or metadata.

19. The method of claim 18 wherein derivation of the first content signature is relatively less computationally intense relative to derivation of the second content signature.

20. The method of claim 18 wherein derivation of the first content signature involves a transform domain analysis.