Identifying image content

• US 20030072491A1
• Filed: 10/17/2001
• Published: 04/17/2003
• Est. Priority Date: 10/17/2001
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Reese, Robert J., Sirivara, Sudheer, McVeigh, Jeffrey S.
• Granted Patent: US 6,961,467 B2
• Time in Patent Office: Days
• US Class Current: 382/220
• CPC Class Codes: G06F 21/10 Protecting distributed programs or content, e.g. vending or licensing of copyrighted material protection in video systems or pay television H04N7/16 ; Digital rights management [DRM]
• CPC Class Codes: H04N 1/00002 Diagnosis, testing or measuring; Detecting, analysing or monitoring not otherwise provided for error detection, error correction or monitoring in digital computers or digital computer components G06F11/00
• CPC Class Codes: H04N 1/00005 relating to image data
• CPC Class Codes: H04N 1/00037 Detecting, i.e. determining the occurrence of a predetermined state H04N1/00031 takes precedence
• CPC Class Codes: H04N 1/00045 using a reference pattern designed for the purpose, e.g. a test chart
• CPC Class Codes: H04N 1/00925 Inhibiting an operation
• CPC Class Codes: H04N 21/23418 involving operations for analysing video streams, e.g. detecting features or characteristics television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/2541 Rights Management protecting software against unauthorised usage in a vending or licensing environment G06F21/10; security in data switching network management H04L41/28; security management or policies for network security H04L63/20; access security in wireless networks H04W12/08
• CPC Class Codes: H04N 21/4788 communicating with other users, e.g. chatting arrangements for providing for computer conferences, e.g. chat rooms, to substation in data switching networks H04L12/1813; distributed application using peer-to-peer [P2P] networks H04L67/104
• CPC Class Codes: H04N 21/8355 involving usage data, e.g. number of copies or viewings allowed
• CPC Class Codes: H04N 2201/3246 of data relating to permitted access or usage, e.g. level of access or usage parameters for digital rights management [DRM] related to still images
• CPC Class Codes: H04N 2201/3274 Storage or retrieval of prestored additional information
• CPC Class Codes: H04N 7/165 Centralised control of user terminal subsequent to an upstream request signal H04N7/17345; Registering at central by two-way working H04N7/17309
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

Identifying content and authorizing sharing thereof based at least in part on extracting feature data from content to be shared and comparing this extracted feature data against a database of extracted feature data for various reference content. When the content to be shared is matched to reference content in the database, sharing may be simply rejected, or rights associated with the reference content may be inspected to facilitate determining authorization.

Claims

1. A method for authorizing transfer of a candidate content against a data store storing extracted feature data for reference content, comprising:

extracting first feature data from the candidate content; and

sending extracted feature data to a sever configured to perform

selecting reference feature data from the data store,

comparing extracted feature data with the reference feature data, and

determining an authorization for transfer of the candidate content based at least in part on the comparing.

2. The method of claim 1, wherein the reference content comprises an image.

3. The method of claim 1, wherein the reference content comprises a video.

4. The method of claim 1, wherein the first feature data is extracted from a central portion of the candidate content.

5. The method of claim 1, wherein extracting first feature data comprises:

apportioning the candidate content into plural sub-regions; and

extracting feature data from the plural sub-regions.

6. The method of claim 5, wherein each sub-region is at most ten percent of the candidate content.

7. The method of claim 5, wherein the sub-regions have at least one dimensional extent less than or equal to 64 pixels.

8. The method of claim 1, wherein extracting first feature data comprises:

apportioning the candidate content into plural sub-regions; and

performing edge detection on the plural sub-regions.

9. The method of claim 1, further comprising:

determining first sub-regions for a first frame of the candidate content;

determining second sub-regions for a second frame of the candidate content;

extracting the first feature data from the first sub-regions; and

extracting a second feature data from the second sub-regions.

10. The method of claim 1, wherein extracting the first feature data comprises selected ones of:

performing edge detection, and detecting motion of an object of the first frame to the second frame.

11. The method of claim 1, further comprising:

performing the method with a network browser plug-in.

12. A method for authorizing transfer of a candidate content against a data storage storing extracted feature data for reference content, comprising:

receiving feature data for the candidate content;

selecting first reference feature data from the data storage,

first comparing the received feature data to the first reference feature data; and

authorizing transfer of the candidate content based at least in part on the first comparing.

13. The method of claim 12, wherein the received feature data comprises extracted feature data for a portion of the candidate content, and the first reference feature data comprises extracted feature data for a first portion of the reference content.

14. The method of claim 13, further comprising:

determining a non-match between the received feature data and the first reference feature data;

selecting second reference feature data from the data storage comprising extracted feature data for a second portion of the reference content; and

second comparing the second reference content to the received feature data.

15. The method of claim 14, wherein the first and the second portions of the reference content overlap.

16. The method of claim 14, further comprising:

performing a sliding window comparison to match the received feature data against the reference content;

wherein the first reference feature data corresponds to a first location of the sliding window on the reference content, and the second reference feature data corresponds to a second location of the sliding window on the reference content.

17. The method of claim 14, wherein the first and second comparing correspond to a comparison of a sliding window on the reference content.

18. The method of claim 12,

selecting second reference feature data from the data storage;

second comparing the received feature data with the second reference feature data; and

determining a degree of similarity between the candidate content and the reference content based at least in part on the first and second comparing.

19. A method for facilitating transfer authorization for a reference content comprising multiple frames, the method comprising, for each frame of the reference content, performing:

determining sub-regions for a current-frame of the reference content;

extracting feature data for the sub-regions; and

storing the extracted feature data in a database.

20. The method of claim 19, further comprising:

storing transfer authorization criteria in the database.

21. The method of claim 19, wherein extracting feature data comprises selected ones of:

performing edge detection, and detecting motion of an object of the first frame to the second frame.

22. An article, comprising:

a machine-accessible media having associated directives for authorizing transfer of a candidate content against a data store storing extracted feature data for reference content, wherein the directives, when accessed, results in a machine performing;

extracting first feature data from the candidate content; and

sending extracted feature data to a sever configured to perform

selecting reference feature data from the data store,

comparing extracted feature data with the reference feature data, and

determining an authorization for transfer of the candidate content based at least in part on the comparing.

23. The article of claim 22, wherein the reference content comprises an image.

24. The article of claim 22, wherein the reference content comprises a video.

25. The article of claim 22, wherein the first feature data is extracted from a central portion of the candidate content.

26. The article of claim 22, wherein the directives for extracting first feature data further includes directives, when accessed by the machine, results in the machine performing:

apportioning the candidate content into plural sub-regions; and

extracting feature data from the plural sub-regions.

27. The article of claim 26, wherein each sub-region is at most ten percent of the candidate content.

28. The article of claim 26, wherein the sub-regions have at least one dimensional extent less than or equal to 64 pixels.

29. The article of claim 22, wherein the directives for extracting first feature data further includes directives, when accessed by the machine, results in the machine performing:

apportioning the candidate content into plural sub-regions; and

performing edge detection on the plural sub-regions.

30. The article of claim 22, wherein the directives further include directives, when accessed by the machine, results in the machine performing:

determining first sub-regions for a first frame of the candidate content;

determining second sub-regions for a second frame of the candidate content;

extracting the first feature data from the first sub-regions; and

extracting a second feature data from the second sub-regions.

31. The article of claim 22, wherein the directives for extracting the first feature data includes directives, when accessed by the machine, results in the machine performing selected ones of:

edge detection, and detecting motion of an object of the first frame to the second frame.

32. The article of claim 22, wherein the directives further include directives, when accessed by the machine, results in the machine performing:

performing the method with a network browser plug-in.

33. An article, comprising:

a machine-accessible media having associated directives for authorizing transfer of a candidate content against a data store storing extracted feature data for reference content, wherein the directives, when accessed, results in a machine performing;

receiving feature data for the candidate content;

selecting first reference feature data from the data storage,

first comparing the received feature data to the first reference feature data; and

authorizing transfer of the candidate content based at least in part on the first comparing.

34. The article of claim 33, wherein the received feature data comprises extracted feature data for a portion of the candidate content, and the first reference feature data comprises extracted feature data for a first portion of the reference content.

35. The article of claim 34, wherein the directives further include directives, when accessed by the machine, results in the machine performing:

determining a non-match between the received feature data and the first reference feature data;

selecting second reference feature data from the data storage comprising extracted feature data for a second portion of the reference content; and

second comparing the second reference content to the received feature data.

36. The article of claim 35, wherein the first and the second portions of the reference content overlap.

37. The article of claim 35, wherein the directives further include directives, when accessed by the machine, results in the machine performing:

performing a sliding window comparison to match the received feature data against the reference content;

wherein the first reference feature data corresponds to a first location of the sliding window on the reference content, and the second reference feature data corresponds to a second location of the sliding window on the reference content.

38. The article of claim 35, wherein the first and second comparing correspond to a comparison of a sliding window on the reference content.

39. The article of claim 33, wherein the directives further include directives, when accessed by the machine, results in the machine performing:

selecting second reference feature data from the data storage;

second comparing the received feature data with the second reference feature data; and

determining a degree of similarity between the candidate content and the reference content based at least in part on the first and second comparing.

42. The article of claim 39, wherein the directives for extracting the first feature data includes directives, when accessed by the machine, results in the machine performing selected ones of:

edge detection, and detecting motion of an object of the first frame to the second frame.

40. An article, comprising:

a machine-accessible media having associated directives for facilitating transfer authorization for a reference content comprising multiple frames, wherein the directives, when accessed, results in a machine performing, for each frame of the reference content;

determining sub-regions for a current-frame of the reference content;

extracting feature data for the sub-regions; and

storing the extracted feature data in a database.

41. The article of claim 40, wherein the directives further include directives, when accessed by the machine, results in the machine performing:

storing transfer authorization criteria in the database.