METHOD AND APPARATUS FOR REDUCING COMPLEXITY OF A COMPUTER VISION SYSTEM AND APPLYING RELATED COMPUTER VISION APPLICATIONS

• US 20130039535A1
• Filed: 03/27/2012
• Published: 02/14/2013
• Est. Priority Date: 08/08/2011
• Status: Abandoned Application

• Current Assignee: MediaTek, Inc.
• Original Assignee: Cheng-Tsai Ho, Chi-Cheng Ju, Ding-Yun Chen
• Inventors: Ho, Cheng-Tsai, Ju, Chi-Cheng, Chen, Ding-Yun
• Application Number:
  US13/431,900
• Publication Number:
  US 20130039535A1
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]

Abstract

A method for reducing complexity of a computer vision system and applying related computer vision applications includes: obtaining instruction information, wherein the instruction information is used for a computer vision application; obtaining image data from a camera module and defining at least one region of recognition corresponding to the image data by user gesture input on a touch-sensitive display; outputting a recognition result of the aforementioned at least one region of recognition; and searching at least one database according to the recognition result. Associated apparatus are also provided. For example, the apparatus includes an instruction information generator, a processing circuit, and a database management module, where the instruction information generator obtains the instruction information, and the processing circuit obtains the image data from the camera module, defines the aforementioned at least one region of recognition and outputs a recognition result of the at least one region of recognition.

Claims

1. A method for reducing complexity of a computer vision system and applying related computer vision applications, the method comprising the steps of:

obtaining instruction information, wherein the instruction information is used for a computer vision application;

obtaining image data from a camera module and defining at least one region of recognition corresponding to the image data by user gesture input on a touch-sensitive display;

outputting a recognition result of the at least one region of recognition; and

searching at least one database according to the recognition result.

2. The method of claim 1, wherein at least one portion of the instruction information is obtained from a global navigation satellite system (GNSS) receiver.

3. The method of claim 1, wherein at least one portion of the instruction information is obtained from an audio input module.

4. The method of claim 1, wherein at least one portion of the instruction information is obtained from the touch-sensitive display.

5. The method of claim 1, wherein the computer vision application is translation.

6. The method of claim 1, wherein the computer vision application is exchange rate conversion.

7. The method of claim 1, wherein the computer vision application is best price search.

8. The method of claim 1, wherein the computer vision application is information search.

9. The method of claim 1, wherein the computer vision application is map browsing.

10. The method of claim 1, wherein the computer vision application is video trailer search.

11. The method of claim 1, further comprising:

performing text recognition on the region of recognition corresponding to the image data to generate the recognition result, wherein the recognition result is a text recognition result.

12. The method of claim 1, further comprising:

performing object recognition on the region of recognition corresponding to the image data to generate the recognition result, wherein the recognition result is a text string representing an object.

13. The method of claim 1, wherein defining the at least one region of recognition corresponding to the image data by the user gesture input on the touch-sensitive display further comprises:

defining the at least one region of recognition to make pauses for a text recognition operation.

14. The method of claim 1, wherein defining the at least one region of recognition corresponding to the image data by the user gesture input on the touch-sensitive display further comprises:

defining the at least one region of recognition to determine object outline(s) for an object recognition operation.

15. The method of claim 1, wherein outputting the recognition result of the at least one region of recognition further comprises:

providing user interface allowing a user to alter the recognition result by additional user gesture input on the touch-sensitive display.

16. The method of claim 15, wherein the step of providing the user interface allowing the user to alter the recognition result by the additional user gesture input on the touch-sensitive display further comprises:

providing the user interface allowing the user to write text under recognition directly by the additional user gesture input on the touch-sensitive display, and performing text recognition.

17. The method of claim 15, wherein the step of providing the user interface allowing the user to alter the recognition result by the additional user gesture input on the touch-sensitive display further comprises:

providing the user interface allowing the user to write a text string representing an object under recognition directly by the additional user gesture input on the touch-sensitive display, and performing text recognition.

18. The method of claim 15, wherein the step of providing the user interface allowing the user to alter the recognition result by the additional user gesture input on the touch-sensitive display further comprises:

performing a learning operation by storing correction information corresponding to mapping relationship between the recognition result and the altered recognition result, for further use of automatic correction of recognition results.

19. The method of claim 1, wherein the step of searching the at least one database according to the recognition result further comprises:

automatically determining whether to utilize a local database or a server on Internet, to perform the computer vision application.

20. The method of claim 1, wherein the step of searching the at least one database according to the recognition result further comprises:

managing local or Internet database access to perform the computer vision application.

21. The method of claim 20, wherein the step of managing the local or Internet database access further comprises:

in a situation where it is automatically determined to utilize a server on Internet to perform the computer vision application, temporarily storing a computer vision application result into a local database, for further use of computer vision applications.

22. The method of claim 20, wherein the step of managing the local or Internet database access further comprises:

according to power management information of the computer vision system, automatically determining whether to utilize a local database or a server on Internet to perform the computer vision application.

23. An apparatus for reducing complexity of a computer vision system and applying related computer vision applications, the apparatus comprising at least one portion of the computer vision system, the apparatus comprising:

an instruction information generator arranged to obtain instruction information, wherein the instruction information is used for a computer vision application;

a processing circuit arranged to obtain image data from a camera module and to define at least one region of recognition corresponding to the image data by user gesture input on a touch-sensitive display, wherein the processing circuit is further arranged to output a recognition result of the at least one region of recognition; and

a database management module arranged to search at least one database according to the recognition result.

24. The apparatus of claim 23, wherein the instruction information generator comprises a global navigation satellite system (GNSS) receiver;

and at least one portion of the instruction information is obtained from the GNSS receiver.

25. The apparatus of claim 23, wherein the instruction information generator comprises an audio input module;

and at least one portion of the instruction information is obtained from the audio input module.

26. The apparatus of claim 23, wherein the instruction information generator comprises the touch-sensitive display;

and at least one portion of the instruction information is obtained from the touch-sensitive display.

27. The apparatus of claim 23, wherein the computer vision application is translation.

28. The apparatus of claim 23, wherein the computer vision application is exchange rate conversion.

29. The apparatus of claim 23, wherein the computer vision application is best price search.

30. The apparatus of claim 23, wherein the computer vision application is information search.

31. The apparatus of claim 23, wherein the computer vision application is map browsing.

32. The apparatus of claim 23, wherein the computer vision application is video trailer search.

33. The apparatus of claim 23, wherein the processing circuit performs text recognition on the region of recognition corresponding to the image data to generate the recognition result, wherein the recognition result is a text recognition result.

34. The apparatus of claim 23, wherein the processing circuit performs object recognition on the region of recognition corresponding to the image data to generate the recognition result, wherein the recognition result is a text string representing an object.

35. The apparatus of claim 23, wherein the processing circuit defines the at least one region of recognition to make pauses for a text recognition operation.

36. The apparatus of claim 23, wherein the processing circuit defines the at least one region of recognition to determine object outline(s) for an object recognition operation.

37. The apparatus of claim 23, wherein the processing circuit provides user interface allowing a user to alter the recognition result by additional user gesture input on the touch-sensitive display.

38. The apparatus of claim 37, wherein the processing circuit provides the user interface allowing the user to write text under recognition directly by the additional user gesture input on the touch-sensitive display, and performs text recognition.

39. The apparatus of claim 37, wherein the processing circuit provides the user interface allowing the user to write a text string representing an object under recognition directly by the additional user gesture input on the touch-sensitive display, and performs text recognition.

40. The apparatus of claim 37, wherein the processing circuit performs a learning operation by storing correction information corresponding to mapping relationship between the recognition result and the altered recognition result, for further use of automatic correction of recognition results.

41. The apparatus of claim 23, wherein the database management module automatically determines whether to utilize a local database or a server on Internet, to perform the computer vision application.

42. The apparatus of claim 23, wherein the database management module manages local or Internet database access to perform the computer vision application.

43. The apparatus of claim 42, wherein in a situation where the database management module automatically determines to utilize a server on Internet to perform the computer vision application, the database management module temporarily stores a computer vision application result into a local database, for further use of computer vision applications.

44. The apparatus of claim 42, wherein according to power management information of the computer vision system, the database management module automatically determines whether to utilize a local database or a server on Internet to perform the computer vision application.