Surrogate heuristic identification

• US 7,991,206 B1
• Filed: 07/02/2007
• Issued: 08/02/2011
• Est. Priority Date: 07/02/2007
• Status: Active Grant

• Current Assignee: Concert Technology Corporation
• Original Assignee: DataScout, Inc.
• Inventors: Kaminski, Charles F. Jr.
• Primary Examiner(s): Mariam; Daniel G
• Application Number:
  US11/824,815
• Time in Patent Office: 1,492 Days
• Field of Search: 382/124, 382/209, 382/218, 382/224, 382/100
• US Class Current: 382/124
• CPC Class Codes: G06F 16/785 using colour or luminescence
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames

Abstract

Surrogate heuristic identification is described, including selecting a portion of video content, wherein the portion is standardized, identifying a characteristic associated with the video content, using the characteristic to generate a data representation, the data representation being used to provide heuristic data, and processing the heuristic data to generate a fingerprint configured to compare against one or more stored fingerprints associated with other video content.

Claims

1. A method, comprising:

selecting, in at least one computing device, a portion of video content, wherein the portion is standardized and corresponds to an area of pixels in which at least a threshold number of the pixels embody a characteristic;

using the characteristic embodied in the portion of the video content to generate a data representation of the portion of the video content, the data representation being used to provide heuristic data; and

processing the heuristic data to generate a fingerprint configured to compare one or more stored fingerprints associated with other video content.

2. The method of claim 1, further comprising storing the fingerprint.

3. The method of claim 1, wherein the video content comprises an image.

4. The method of claim 1, wherein the characteristic is brightness meeting a brightness threshold.

5. The method of claim 1, wherein the characteristic is a color channel value meeting a color channel value threshold.

6. The method of claim 1, wherein the fingerprint comprises encoded heuristic data.

7. The method of claim 1, wherein the portion comprises all of the video content.

8. The method of claim 1, wherein the heuristic data comprises one or more vectors.

9. The method of claim 1, wherein the heuristic data comprises a histogram.

10. The method of claim 1, wherein the heuristic data comprises vector data and histogram data.

11. The method of claim 1, wherein processing the heuristic data further comprises using heuristic data to generate the fingerprint.

12. The method of claim 1, wherein processing the heuristic data further comprises generating a hash value using a first hashing algorithm.

13. The method of claim 1, wherein a first hashing algorithm is run against the fingerprint to generate a first hash value.

14. The method of claim 13, wherein a second hashing algorithm that is different from the first hashing algorithm is run against the fingerprint to generate a second hash value.

15. The method of claim 1, wherein the heuristic data is normalized.

16. The method of claim 1, wherein generating the histogram comprises counting occurrences of the characteristic.

17. The method of claim 1, wherein the characteristic is contrast meeting a contrast threshold.

18. The method of claim 1, wherein the characteristic is pixel density meeting a pixel density threshold.

19. The method of claim 1, further comprising:

running a first hashing algorithm against the portion to generate a first hash value, and running a second hashing algorithm against the portion to generate a second hash value, wherein the first hashing algorithm and the second hashing algorithm are different;

determining whether the first hash value and the second hash value are substantially similar to one or more stored hash values associated with another portion, the another portion being substantially similar to the portion; and

identifying a location of the video content associated with the portion if the first hash value and second hash value are substantially similar to the one or more stored hash values.

20. A computer program product embodied in a non-transitory computer readable medium, comprising computer instructions for:

selecting a portion of video content, wherein the portion is standardized and corresponds to an area of pixels in which at least a threshold number of the pixels embody a characteristic;

using the characteristic embodied in the portion of the video content to generate a data representation of the portion of the video content, the data representation being used to provide heuristic data; and

processing the heuristic data to generate a fingerprint configured to compare against one or more stored fingerprints associated with other video content.

21. A system, comprising:

means for selecting a portion of video content in at least one computing device, wherein the portion is standardized and corresponds to an area of pixels in which at least a threshold number of the pixels embody a characteristic;

means for using the characteristic embodied in the portion of the video content to generate a data representation of the portion of the video content, the data representation being used to provide heuristic data; and

means for processing the heuristic data to generate a fingerprint configured to compare against one or more stored fingerprints associated with other video content.