Robust recognizer of perceptually similar content

• US 20020196976A1
• Filed: 04/24/2001
• Published: 12/26/2002
• Est. Priority Date: 04/24/2001
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Venkatesan, Ramarathnam, Mihcak, M. Kivanc
• Granted Patent: US 6,996,273 B2
• Time in Patent Office: Days
• US Class Current: 382/173
• CPC Class Codes: G06F 18/00 Pattern recognition

Abstract

An implementation of a technology is described herein for recognizing the perceptual similarity of the content of digital goods. At least one implementation, described herein, introduces a new hashing technique. More particularly, this hashing technique produces hash values for digital goods that are proximally near each other, when the digital goods contain perceptually similar content. In other words, if the content of digital goods are perceptually similar, then their hash values are, likewise, similar. The hash values are proximally near each other. This is unlike conventional hashing techniques where the hash values of goods with perceptually similar content are far apart with high probability in some distance sense (e.g., Hamming). This abstract itself is not intended to limit the scope of this patent. The scope of the present invention is pointed out in the appending claims.

Claims

1. A computer-implemented method facilitating similarity recognition of a digital signal, the method comprising:

obtaining a digital signal; and

deriving a recognition value representative of the digital signal such that perceptually distinct digital signals result in recognition values that are approximately independent of one another and perceptually similar digital signals result in proximally similar recognition values.

2. A method as recited in claim 1 further comprising comparing the recognition value with another recognition value derived from another digital signal.

3. A method as recited in claim 1, wherein the recognition value is a hash value.

4. A method as recited in claim 1, wherein the digital signals are digital image signals.

5. A computer-readable medium having computer-executable instructions that, when executed by a computer, performs the method as recited in claim 1.

6. A computer comprising one or more computer-readable media having computer-executable instructions that, when executed by the computer, perform the method as recited in claim 1.

7. A method for hashing a digital signal, the method comprising:

transforming a digital signal into a digital signal transform;

quantizing the digital signal transform;

geometric-region-growing the digital signal transform;

generating a recognition value of the digital signal.

8. A method as recited in claim 7 further comprising:

pseudorandomly segmenting the digital signal into one or more segments;

for one or more of the segments, repeating the transforming, the quantizing, and the geometric-region-growing, wherein these repeated tasks are performed on a segment rather than the entire signal;

combining one or more of the segments.

9. A method as recited in claim 7, wherein the transforming comprises a discrete wavelet transformation of the digital signal.

10. A method as recited in claim 7, wherein the transforming comprises finding the DC subband.

11. A method as recited in claim 7, wherein the quantizing comprises a multi-level quantization of the digital signal transform.

12. A method as recited in claim 7, wherein the recognition value is a hash value.

13. A method as recited in claim 7, wherein the geometric-region-growing comprises iterative geometric conversion.

14. A method as recited in claim 7, wherein the geometric-region-growing comprises self-correcting iterative filtering.

15. A method as recited in claim 7, wherein the geometric-region-growing comprises accentuating geometrically strong components of the signal while de-emphasizing the geometrically weak components of the signal.

16. A method as recited in claim 7, wherein the geometric-region-growing growing comprises order-statistics filtering, local smoothing, and quantizing.

17. A method as recited in claim 16, wherein the local smoothing comprises multi-dimensional linear shift-invariant filtering.

18. A computer-readable medium having computer-executable instructions that, when executed by a computer, performs the method as recited in claim 7.

19. A computer comprising one or more computer-readable media having computer-executable instructions that, when executed by the computer, perform the method as recited in claim 7.

20. A method for hashing a digital signal, the method comprising:

transforming a digital signal into a digital signal transform;

quantizing the digital signal transform;

self-correcting iterative filtering of the digital signal transform;

generating a recognition value of the digital signal.

21. A method as recited in claim 20 further comprising:

pseudorandomly segmenting the digital signal into one or more segments;

for one or more of the segments, repeating the transforming, the quantizing, and the self-correcting iterative filtering, wherein these repeated tasks are performed on a segment rather than the entire signal;

combining one or more of the segments.

22. A method as recited in claim 20, wherein the quantizing comprises a multi-level quantization of the digital signal transform.

23. A method as recited in claim 20, wherein the recognition value is a hash value.

24. A method as recited in claim 20, wherein the self-correcting iterative filtering comprises accentuating geometrically strong components of the signal while de-emphasizing the geometrically weak components of the signal.

25. A method as recited in claim 20, wherein the self-correcting iterative filtering comprises order-statistics filtering, local smoothing, and quantizing.

26. A computer-readable medium having computer-executable instructions that, when executed by a computer, performs the method as recited in claim 20.

27. A computer comprising one or more computer-readable media having computer-executable instructions that, when executed by the computer, perform the method as recited in claim 20.

29. A method as recited in claim 28, wherein the recognition value is a hash value.

30. A computer-readable medium having computer-executable instructions that, when executed by a computer, performs the method as recited in claim 28.

31. A computer comprising one or more computer-readable media having computer-executable instructions that, when executed by the computer, perform the method as recited in claim 28.

28. A method for hashing a digital signal, the method comprising:

pseudorandomly segmenting a digital signal into one or more segments;

for one or more of the segments;

transforming a segment into a segment transform;

quantizing the segment transform;

self-correcting iterative filtering of the segment transform;

combining one or more of the segments;

generating a recognition value of the digital signal.

32. A computer-implemented method facilitating similarity recognition of a digital signal, the method comprising:

obtaining a digital signal;

non-linear filtering of the signal to eliminate isolated significant components of the signal;

deriving a recognition value from the filtered signal, the recognition value being representative of the digital signal such that perceptually distinct digital signals result in recognition values that are approximately independent of one another and perceptually similar digital signals result in proximally similar recognition values.

33. A method as recited in claim 32, wherein isolated significant components of the signal are those that are geometrically weak.

34. A computer-readable medium having computer-executable instructions that, when executed by a computer, performs the method as recited in claim 32.

36. A system as recited in claim 35 further comprising:

a segmenter configured to pseudorandomly segment the digital signal into one or more segments;

a combiner configured to combine the output of the converter for one or more of the segments.

35. A system for digital signal similarity recognition, the system comprising:

a transformer configured to transform a digital signal into a signal transform;

a quantizer configured to quantitize the signal transform;

a iterative geometric converter configured to convert the signal transform into a representation of the signal that emphasizes geometrically strong components of the signal while de-emphasizing geometrically weak components of the signal.

37. A system for digital signal similarity recognition, the system comprising:

a segmenter configured to pseudorandomly segment the digital signal into one or more of the segments;

a transformer configured to transform a segment into a segment transform;

a quantizer configured to quantitize the segment transform;

a iterative geometric converter configured to convert the segment transform into a representation of the segment that emphasizes geometrically strong components of the segment while de-emphasizing geometrically weak components of the segment;

a combiner configured to combine the output of the converter for one or more of the segments.

38. A computer-readable medium having computer-executable instructions that, when executed by a computer, performs the method comprising:

obtaining a digital signal; and

deriving a recognition value representative of the digital signal such that perceptually distinct digital signals result in recognition values that are approximately independent of one another and perceptually similar digital signals result in proximally similar recognition values.

39. A computer-readable medium having computer-executable instructions that, when executed by a computer, performs the method comprising:

transforming a digital signal into a digital signal transform;

quantizing the digital signal transform;

self-correcting iterative filtering of the digital signal transform;

generating a recognition value of the digital signal.