Methods, apparatus and programs for generating and utilizing content signatures

• US 7,974,436 B2
• Filed: 09/28/2006
• Issued: 07/05/2011
• Est. Priority Date: 12/21/2000
• Status: Active Grant

• Current Assignee: Digimarc Corporation
• Original Assignee: Digimarc Corporation
• Inventors: Levy, Kenneth L., Brunk, Hugh L.
• Primary Examiner(s): TUCKER, WESLEY J
• Application Number:
  US11/536,487
• Publication Number:
  US 20070033409A1
• Time in Patent Office: 1,741 Days
• Field of Search: 382/100, 382276-281
• US Class Current: 382/100
• 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 relates to deriving and/or utilizing content signatures. A content signature includes a representation of a content item, which is derived or calculated from the content item itself. One claim recites a method comprising: obtaining a content item; transforming the content item to obtain transform domain coefficients; applying Viterbi decoding to a set of the transform domain coefficients; and using a result of the Viterbi decoding as a content signature representing features or characteristics of the content item itself. Other claims and combinations are provided too.

Claims

1. A method comprising:

obtaining a content item;

transforming the content item to obtain transform domain coefficients;

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

using a result of the Viterbi decoding as a content signature representing features or characteristics of the content item itself.

2. The method of claim 1, wherein the act of transforming utilizes a wavelet transformation.

3. The method of claim 1, wherein the set of the transform domain coefficients corresponds to low frequency coefficients.

4. A method of claim 1, wherein the content signature comprises a reduced-bit representation of the content item.

14. An apparatus comprising a processor programmed to perform the act of applying Viterbi decoding of claim 1.

15. An apparatus comprising a processor programmed to perform the act of applying Viterbi decoding of claim 2.

16. An apparatus comprising a processor programmed to perform the act of applying Viterbi decoding of claim 3.

5. A non-transitory machine-readable medium having instructions stored thereon that, the instructions comprising:

instructions to obtain a content item;

instructions to transform the content item to obtain transform domain coefficients;

instructions to apply Viterbi decoding to a set of the transform domain coefficients; and

instructions to use a result of the Viterbi decoding as a content signature representing features or characteristics of the content item itself.

6. The non-transitory machine-readable medium of claim 5, wherein the act of transforming utilizes a wavelet transformations.

7. A method comprising:

performing a decomposition on a media signal to provide a plurality of components representing the media signal;

identifying a subset of the plurality of components; and

applying Viterbi decoding to the subset to generate a content signature or fingerprint representative of the media signal itself.

8. The method of claim 7, wherein the media signal comprises audio or video.

9. The method of claim 7, wherein the decomposition comprises a wavelet decomposition.

10. The method of claim 7, wherein the subset comprises coefficients of a lowest frequency sub-band of the media signal.

17. An apparatus comprising a processor programmed to perform the act of applying Viterbi decoding of claim 7.

18. An apparatus comprising a processor programmed to perform the act of applying Viterbi decoding of claim 9.

19. An apparatus comprising a processor programmed to perform the act of applying Viterbi decoding of claim 10.

11. A non-transitory machine-readable medium having instructions stored thereon the instructions comprising:

instructions to perform a decomposition on a media signal to provide a plurality of components representing the media signal;

instructions to identify a subset of the plurality of components; and

instructions to apply Viterbi decoding to the subset to generate a content signature or fingerprint representative of the media signal itself.

12. The non-transitory machine-readable medium of claim 11, wherein the decomposition comprises a wavelet decomposition.

13. The non-transitory machine-readable medium of claim 11, wherein the subset comprises coefficients of a lowest frequency sub-band of the media signal.

20. An apparatus comprising:

a memory configured to buffer data representing a content item; and

a processor configured to;

transform the data to obtain transform domain coefficients;

apply Viterbi decoding to a set of the transform domain coefficients; and

use a result of the Viterbi decoding as a content signature representing features or characteristics of the content item itself.

21. The apparatus of claim 20, wherein the transforming utilizes a wavelet transformation.

22. The apparatus of claim 20, wherein the set of the transform domain coefficients corresponds to low frequency coefficients.

23. The apparatus of claim 20, wherein the content signature comprises a reduced-bit representation of the content item.

24. An apparatus comprising:

a memory configured to buffer data representing a media signal; and

a processor configured to;

perform a decomposition on the data to provide a plurality of components representing the media signal;

identify a subset of the plurality of components; and

apply Viterbi decoding to the subset to generate a content signature or fingerprint representative of the media signal itself.

25. The apparatus of claim 24, wherein the media signal comprises audio or video.

26. The apparatus of claim 24, wherein the decomposition comprises a wavelet decomposition.

27. The apparatus of claim 24, wherein the subset comprises coefficients of a lowest frequency sub-band of the media signal.

28. An apparatus comprising:

means for buffering data representing a content item;

means for transforming the data to obtain transform domain coefficients;

means for applying Viterbi decoding to a set of the transform domain coefficients; and

means for using a result of the Viterbi decoding as a content signature representing characteristics or features the content item itself.

29. The apparatus of claim 28, wherein the means for transforming utilizes a wavelet transformation.

30. The apparatus of claim 29, wherein the set of the transform domain coefficients corresponds to low frequency coefficients.

31. The apparatus of claim 28, wherein the content signature comprises a reduced-bit representation of the content item.

32. An apparatus comprising:

means for buffering data representing a media signal;

means for performing a decomposition on the data to provide a plurality of components representing the media signal;

means for identifying a subset of the plurality of components; and

means for applying Viterbi decoding to the subset to generate a content signature or fingerprint representative of the media signal itself.

33. The apparatus of claim 32, wherein the media signal comprises audio or video.

34. The apparatus of claim 32, wherein the decomposition comprises a wavelet decomposition.

35. The apparatus of claim 32, wherein the subset comprises coefficients of a lowest frequency sub-band of the media signal.

36. The apparatus of claim 32, wherein the content signature is utilized to track the media signal.