Comparison of data signals using characteristic electronic thumbprints extracted therefrom

• US 7,853,438 B2
• Filed: 07/31/2008
• Issued: 12/14/2010
• Est. Priority Date: 04/24/2001
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Auditude Incorporated (Adobe Inc.)
• Inventors: Seet, Nicholas, Yeager, William Shawn, Caruso, Jeffery L.
• Primary Examiner(s): Kundu; Sujoy K
• Application Number:
  US12/183,824
• Publication Number:
  US 20090034807A1
• Time in Patent Office: 866 Days
• Field of Search: 702189-190, 341/155, 704/205, 704/222, 704/229
• US Class Current: 702/190
• CPC Class Codes: G06F 16/634 Query by example, e.g. query by humming
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G10H 2210/031 Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
• CPC Class Codes: G10H 2240/141 Library retrieval matching, i.e. any of the steps of matching an inputted segment or phrase with musical database contents, e.g. query by humming, singing or playing; the steps may include, e.g. musical analysis of the input, musical feature extraction, query formulation, or details of the retrieval process

Abstract

A characteristic thumbprint is extracted from a data signal, the thumbprint based on statistics relating to the data signal. The data signal can be compared indirectly by matching this thumbprint against one or more reference thumbprints. The data signal may be any type of signal, including streaming digitized audio or obtained from static files. A database may contain a number of these characteristic thumbprints, and the database can be searched for a particular thumbprint.

Claims

1. A method for extracting a digital thumbprint based on at least a portion of a time-dependent data signal, the method comprising:

filtering the data signal to produce a plurality of filtered signals, at least two of the filtered signals having a different frequency range;

computing a measure of power contained within at least a segment of each filtered signal;

determining, by a computer processor, a plurality of coordinates for a digital thumbprint, wherein each coordinate is determined based on the computed measures of power; and

writing a digital thumbprint to a non-transitory computer-readable storage medium, the digital thumbprint comprising the plurality of coordinates determined for the digital thumbprint.

2. The method of claim 1, wherein the data signal contains encoded media content.

3. The method of claim 1, wherein the data signal contains encoded audio content.

4. The method of claim 1, wherein the data signal contains encoded video content.

5. The method of claim 1, further comprising:

receiving the data signal as streaming media over a network.

6. The method of claim 1, further comprising:

receiving the data signal in real time over a network.

7. The method of claim 1, further comprising:

sampling a broadcast signal to obtain the data signal.

8. The method of claim 1, wherein filtering the data signal to produce a plurality of filtered signals is performed on a digital data signal by a computer processor.

9. The method of claim 1, wherein the method is performed by embedded hardware in a device.

10. The method of claim 1, wherein the plurality of filtered signals have frequency ranges that are in a logarithmically even fashion.

11. The method of claim 1, wherein computing a measure of power contained within at least a segment of each filtered signal comprises locating a local peak for the segment of the filtered signal.

12. The method of claim 1, wherein the measure of power contained within at least a segment of a filtered signal comprises the root-mean-square amplitudes for each of a series of samples of the particular filtered signal.

13. The method of claim 1, wherein the measure of power contained within at least a segment of a filtered signal is a function of the root-mean-square amplitude of a series of samples from the segment of the filtered signal.

14. The method of claim 1, wherein each coordinate is determined using a statistical function comprising the ratio of the standard deviation to the mean of the measures of power computed for the filtered signal.

15. The method of claim 1, wherein the filtering and computing steps are performed by one or more analog circuits.

16. The method of claim 15, wherein the filtering is performed by a set of bandpass filters.

17. The method of claim 15, wherein the determining and writing steps are performed by one or more digital circuits.

18. A method of creating a database of digital fingerprints, the method comprising:

generating a digital thumbprint for each of a plurality of data signals by;

filtering the data signal to produce a plurality of filtered signals, at least two of the filtered signals having a different frequency range,

computing a measure of power contained within at least a segment of each filtered signal,

determining, by a computer processor, a plurality of coordinates for a digital thumbprint, wherein each coordinate is determined based on the computed measures of power, and

creating a digital thumbprint comprising the plurality of coordinates determined for the digital thumbprint;

storing the computed digital thumbprints in a database; and

indexing each digital thumbprint in the database by at least one of the coordinates of the digital thumbprint.

19. The method of claim 18, wherein the indexing comprises creating a tree structure comprising nodes that organize the digital thumbprints according to one or more of their coordinates.

20. The method of claim 18, further wherein the database comprises a plurality of digital fingerprints generated for each of a series of overlapping time segments of the same data signal.

21. The method of claim 18, wherein the filtering and computing steps are performed by one or more analog circuits.

22. The method of claim 21, wherein the filtering is performed by a set of bandpass filters.

23. The method of claim 21, wherein the determining and writing steps are performed by one or more digital circuits.

24. A computer program product for extracting a digital thumbprint based on at least a portion of a time-dependent data signal, the computer program product comprising a non-transitory computer-readable storage medium containing computer program code for:

filtering the data signal to produce a plurality of filtered signals, at least two of the filtered signals having a different frequency range;

computing a measure of power contained within at least a segment of each filtered signal;

determining, by a computer processor, a plurality of coordinates for a digital thumbprint, wherein each coordinate is determined based on the computed measures of power; and

writing a digital thumbprint to the non-transitory computer-readable storage medium, the digital thumbprint comprising the plurality of coordinates determined for the digital thumbprint.

25. The computer program product of claim 24, further containing computer program code for:

receiving the data signal as streaming media over a network.

26. The computer program product of claim 24, further containing computer program code for:

receiving the data signal in real time over a network.

27. The computer program product of claim 24, further containing computer program code for:

sampling a broadcast signal to obtain the data signal.

28. The computer program product of claim 24, wherein the plurality of filtered signals have frequency ranges that are in a logarithmically even fashion.

29. The computer program product of claim 24, wherein the measure of power contained within at least a segment of a filtered signal comprises the root-mean-square amplitudes for each of a series of samples of the particular filtered signal.

30. The computer program product of claim 24, wherein the measure of power contained within at least a segment of a filtered signal is a function of the root-mean-square amplitude of a series of samples from the segment of the filtered signal.

31. The computer program product of claim 24, wherein computing a measure of power contained within at least a segment of each filtered signal comprises locating a local peak for the segment of the filtered signal.

32. The computer program product of claim 24, wherein each coordinate is determined using a statistical function comprising the ratio of the standard deviation to the mean of the measures of power computed for the filtered signal.

33. An article of manufacture comprising a non-transitory computer-readable storage medium containing a digital thumbprint that is characteristic of a data signal, wherein the article of manufacture is made by:

filtering the data signal to produce a plurality of filtered signals, at least two of the filtered signals having a different frequency range;

computing a measure of power contained within at least a segment of each filtered signal;

determining, by a computer processor, a plurality of coordinates for the digital thumbprint, wherein each coordinate is determined based on the computed measures of power; and

writing the digital thumbprint to the non-transitory computer-readable storage medium, the digital thumbprint comprising the plurality of coordinates determined for the digital thumbprint.

34. The article of manufacture of claim 33, wherein the digital thumbprint that is characteristic of a data signal that contains encoded media content.

35. The article of manufacture of claim 33, wherein the digital thumbprint that is characteristic of a data signal that contains encoded audio content.

36. The article of manufacture of claim 33, wherein the digital thumbprint that is characteristic of a data signal that contains encoded video content.

37. The article of manufacture of claim 33, wherein the article of manufacture is further made by:

receiving the data signal as streaming media over a network.

38. The article of manufacture of claim 33, wherein the article of manufacture is further made by:

receiving the data signal in real time over a network.

39. The article of manufacture of claim 33, wherein the article of manufacture is further made by:

sampling a broadcast signal to obtain the data signal.

40. The article of manufacture of claim 33, wherein the plurality of filtered signals have frequency ranges that are in a logarithmically even fashion.

41. The article of manufacture of claim 33, wherein the measure of power contained within at least a segment of a filtered signal comprises the root-mean-square amplitudes for each of a series of samples of the particular filtered signal.

42. The article of manufacture of claim 33, wherein the measure of power contained within at least a segment of a filtered signal is a function of the root-mean-square amplitude of a series of samples from the segment of the filtered signal.

43. The article of manufacture of claim 33, wherein computing a measure of power contained within at least a segment of each filtered signal comprises locating a local peak for the segment of the filtered signal.

44. The article of manufacture of claim 33, wherein each coordinate is determined using a statistical function comprising the ratio of the standard deviation to the mean of the measures of power computed for the filtered signal.

45. The article of manufacture of claim 33, wherein the filtering and computing steps are performed by one or more analog circuits.

46. The article of manufacture of claim 45, wherein the filtering is performed by a set of bandpass filters.

47. The article of manufacture of claim 45, wherein the determining and writing steps are performed by one or more digital circuits.

48. A database comprising a plurality of digital thumbprints stored on a non-transitory computer-readable storage medium, each thumbprint as claimed in claim 33.

49. The database of claim 48, wherein each digital thumbprint in the database is indexed by at least one of the coordinates of the digital thumbprint.

50. The database of claim 48, wherein a plurality of the digital fingerprints are generated for each of a series of overlapping time segments of the same data signal.