Image area extraction method, image reconstruction method using the extraction result and apparatus thereof

• US 7,356,190 B2
• Filed: 06/30/2003
• Issued: 04/08/2008
• Est. Priority Date: 07/02/2002
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Mizoguchi, Shigeru, Suzuki, Naohisa
• Primary Examiner(s): Bella; Matthew C.
• Assistant Examiner(s): BAYAT, ALI
• Application Number:
  US10/608,001
• Publication Number:
  US 20040071352A1
• Time in Patent Office: 1,744 Days
• Field of Search: 382/232, 382/233, 382/236, 382/240, 382/245, 382/246, 382/250, 382/251, 382/166, 382/167, 382/274, 382/190, 382/199, 358/518, 358/519, 358/520, 358/521, 358/522, 358/523, 358/1.9, 375/240, 375/240.03, 375/240.12, 375/240.16, 375/240.2, 348/14.13
• US Class Current: 382/233
• CPC Class Codes: G06V 40/162 using pixel segmentation or colour matching

Abstract

An image area of interest in an image file can be detected by a method with a relatively light processing load by making a determination using characteristics of a quantization table. Since spatial frequency information, chromaticity information, and a quantization table are acquired for respective predetermined blocks from inputted compressed image data, and are used in combination upon searching the compression-recorded image data for an image of interest, information containing AC component information for each image data block is acquired without any advanced calculations, thus searching for the image of interest in the image file.

Claims

1. A method of recognizing an image area of interest from compressed image data through a process for reconstructing decompressed image data from the compressed image data, comprising the steps of:

acquiring spatial frequency information and chromaticity information for respective predetermined blocks from the compressed image data; and

searching for the image area of interest from the compressed image data using the acquired spatial frequency information and chromaticity information.

2. A method according to claim 1, further comprising a step of decompressing the compressed image data, wherein in said acquiring step, the spatial frequency information and chromaticity information are acquired from the decompressed image data.

3. Method according to claim 2, further comprising the steps of:

acquiring quantization parameters for decompression; and

stopping extraction of the image area of interest in accordance with the acquired quantization parameters.

4. A method according to claim 2, wherein the compressed image data comprises JPEG image data and the decompressed image data includes DCT coefficients and bit map data.

5. A method according to claim 1, wherein said searching step comprises the steps of:

extracting consecutive blocks having a predetermined range of chromaticity values; and

determining whether or not the extracted consecutive blocks are the image area of interest based on an average of spatial frequency values within the extracted consecutive blocks.

6. A method according to claim 5, wherein a threshold level for determining whether or not the extracted consecutive blocks are the image area of interest is changed in accordance with a size of image to be extracted.

7. A method according to claim 5, wherein said searching step further comprises a step of selecting candidates of the image area of interest based on a number of the extracted consecutive blocks.

8. A method according to claim 7, wherein a threshold level for selecting candidates of the image area of interest is changed in accordance with a size of image to be extracted.

9. A computer-readable medium storing a computer program for causing a computer to execute the method according to claim 1.

10. A method of recognizing an image area of interest from compressed image data and decoding image data from the compressed image data, through a process for reconstructing decompressed image data from the compressed image data, comprising the steps of:

recognizing an image area of interest from the compressed image data; and

reconstructing an image with correction of image data in the image area of interest to a predetermined value,

wherein said recognizing step comprises the steps of;

acquiring spatial frequency information and chromaticity information for respective predetermined blocks from the compressed image data; and

searching for the image area of interest from the compressed image data using the acquired spatial frequency information and chromaticity information.

11. A method according to claim 10, wherein the predetermined value comprises a predetermined chromaticity value.

12. A method according to claim 10, wherein said recognizing step further comprises a step of decompressing the compressed image data, and wherein in said acquiring step, the spatial frequency information and chromaticity information are acquired from the decompressed image data.

13. A method according to claim 12, further comprising the steps of:

acquiring quantization parameters for decompression; and

stopping extraction of the image area of interest in accordance with the acquired quantization parameters.

14. A method according to claim 12, wherein the compressed image data comprises JPEG image data and the decompressed image data includes DCT coefficients and bit map data.

15. A method according to claim 10, wherein said searching step comprises the steps of:

extracting consecutive blocks having a predetermined range of chromaticity value; and

determining whether or not the extracted consecutive blocks are the image area of interest based on an average of spatial frequency values within the extracted consecutive blocks.

16. A method according to claim 15, wherein a threshold level for determining whether or not the extracted consecutive blocks are the image area of interest is changed in accordance with a size of image to be extracted.

17. A method according to claim 15, wherein said searching step further comprises a step of selecting candidates of the image area of interest based on a number of the extracted consecutive blocks.

18. A method according to claim 17, wherein a threshold level for selecting candidates of the image area of interest is changed in accordance with a size of image to be extracted.

19. A computer-readable medium storing a computer program for causing a computer to execute the method according to claim 10.

20. An image processing apparatus for recognizing an image area of interest from compressed image data through a process for reconstructing decompressed image data from the compressed image data, comprising:

acquiring means for acquiring spatial frequency information and chromaticity information for respective predetermined blocks from the compressed image data; and

searching means for searching for the image area of interest from the compressed image data using the spatial frequency information and chromaticity information acquired by said acquiring means.

21. An apparatus according to claim 20, further comprising decompressing means for decompressing the compressed image data, wherein in said acquiring step, the spatial frequency information and chromaticity information are acquired from the decompressed image data.

22. An apparatus according to claim 21, further comprising:

second acquiring means for acquiring quantization parameters for decompression; and

stopping means for stopping extraction of the image area of interest in accordance with the quantization parameters acquired by said second acquiring means.

23. An apparatus according to claim 21, wherein the compressed image data comprises JPEG image data and the decompressed image data includes DCT coefficients and bit map data.

24. An apparatus according to claim 20, wherein said searching means comprises:

extracting means for extracting consecutive blocks having a predetermined range of chromaticity values; and

determining means for determining whether or not the extracted consecutive blocks are the image area of interest based on an average of spatial frequency values within the extracted consecutive blocks.

25. An apparatus according to claim 24, wherein a threshold level for determining whether or not the extracted consecutive blocks are the image area of interest is changed in accordance with a size of image to be extracted.

26. An apparatus according to claim 24, wherein said searching means further comprises selecting means for selecting candidates of the image area of interest based on a number of the extracted consecutive blocks.

27. An apparatus according to claim 26, wherein a threshold level for selecting candidates of the image area of interest is changed in accordance with a size of image to be extracted.

28. An image processing apparatus for recognizing an image area of interest from compressed image data and decoding image data from the compressed image data, through a process for reconstructing decompressed image data from the compressed image data, comprising:

recognizing means for recognizing an image area of interest from the compressed image data; and

reconstructing means for reconstructing an image with correction of image data in the image area of interest to a predetermined value,

wherein said recognizing means comprises;

acquiring means for acquiring spatial frequency information and chromaticity information for respective predetermined blocks from the compressed image data; and

searching means for searching for the image area of interest from the compressed image data using the acquired spatial frequency information and chromaticity information.

29. An apparatus according to claim 28, wherein the predetermined value comprises a predetermined chromaticity value.

30. An apparatus according to claim 28, wherein said recognizing means further comprises decompressing means for decompressing the compressed image data, and wherein said acquiring means acquires the spatial frequency information and chromaticity information from the decompressed image data.

31. An apparatus according to claim 30, further comprising:

second acquiring means for acquiring quantization parameters for decompression; and

stopping means for stopping extraction of the image area of interest in accordance with the acquired quantization parameters.

32. An apparatus according to claim 30, wherein the compressed image data comprises JPEG image data and the decompressed image data includes DCT coefficients and bit map data.

33. An apparatus according to claim 32, wherein said searching means further comprises means for selecting ca2ndidates of the image area of interest based on a number of the extracted consecutive blocks.

34. An apparatus according to claim 33, wherein a threshold level for selecting candidates of the image area of interest is changed in accordance with a size of image to be extracted.

35. An apparatus according to claim 28, wherein said searching means comprises:

extracting means for extracting consecutive blocks having a predetermined range of chromaticity values; and

determining means for determining whether or not the extracted consecutive blocks are the image area of interest based on an average of spatial frequency values within the extracted consecutive blocks.

36. An apparatus according to claim 35, wherein a threshold level for determining whether or not the extracted consecutive blocks are the image area of interest is changed in accordance with a size of image to be extracted.