Robust recognizer of perceptually similar content

• US 7,406,195 B2
• Filed: 08/15/2005
• Issued: 07/29/2008
• Est. Priority Date: 04/24/2001
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Mihcak, M. Kivanc, Venkatesan, Ramarathnam
• Primary Examiner(s): LAROSE, COLIN M
• Application Number:
  US11/203,940
• Publication Number:
  US 20050273617A1
• Time in Patent Office: 1,079 Days
• Field of Search: 382/181, 382/190, 382/201, 382/206, 382/207, 382/224
• US Class Current: 382/190
• 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, wherein the deriving comprises transforming the digital signal to a frequency domain and hashing the transformed digital signal to produce the recognition value representative of the digital signal.

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 signal is a digital image signal.

5. 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.

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

obtaining a digital signal;

transforming the digital signal to generate a transformed signal in a frequency domain;

non-linear filtering of the transformed signal to eliminate isolated significant components of the signal and generate a filtered 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, wherein the deriving comprises hashing the filtered signal to produce the recognition value representative of the digital signal.

7. A method as recited in claim 6, wherein isolated significant components of the signal are those that are geometrically weak.

8. A computer-readable medium having computer-executable instructions that, when executed by a computer, performs the method as recited in claim 6.

9. A computer-readable medium having computer-executable instructions that, when executed by a computer, performs a 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, wherein the deriving comprises;

transforming the digital signal to a frequency domain;

quantizing the digital signal that has been transformed to eliminate isolated significant components of the digital signal; and

hashing the digital signal that has been quantized to produce the recognition value representative of the digital signal.