Image blur detection methods and arrangements

• US 6,548,800 B2
• Filed: 04/09/2001
• Issued: 04/15/2003
• Est. Priority Date: 04/09/2001
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Zhang, Hong-Jiang, Chen, Xiangrong
• Primary Examiner(s): Epps, Georgia
• Assistant Examiner(s): HANIG, RICHARD E
• Application Number:
  US09/833,525
• Publication Number:
  US 20020145106A1
• Time in Patent Office: 736 Days
• Field of Search: 250/208.1, 382/254, 382/266
• US Class Current: 250/208.1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 7/13 Edge detection

Abstract

An apparatus is provided for detecting blur in an image. The apparatus includes an image generator that is configured to generate a plurality of corresponding different resolution images based on a base image. The plurality of corresponding different resolution images is provided to an edge detector. The edge detector detects edge transitions in each of the plurality of corresponding different resolution images and provides edge maps to an edge parameter comparator. The edge parameter comparator compares corresponding edge parameters as detected by the edge detector and provides a result map to a blur calculator. The blur calculator determines at least one blur parameter based on the result map and provides the blur parameter to a blur detector. The blur detector then determines if the base image is blurred based on a comparison of the blur parameter with at least one blur parameter threshold.

Claims

1. A method comprising:

detecting edges in a plurality of corresponding different resolution images; and

for each detected edge, comparing corresponding edge parameters associated with the detected edges in the plurality of corresponding different resolution images and determining if the detected edge is blurred.

2. The method as recited in claim 1, wherein the corresponding edge parameters associated with the detected edges in the plurality of corresponding different resolution images includes corresponding edge amplitudes associated with the detected edges in the plurality of corresponding different resolution images.

3. The method as recited in claim 1, further comprising generating the plurality of corresponding different resolution images from a base image.

4. The method as recited in claim 3, wherein the plurality of corresponding different resolution images includes the base image and at least one corresponding lower resolution image.

5. The method as recited in claim 3, wherein the plurality of corresponding different resolution images includes the base image a second corresponding lower resolution image, and a third corresponding lower resolution image that is also lower in resolution than the second corresponding lower resolution image.

6. The method as recited in claim 3, wherein the base image is a portion of a larger original image.

7. The method as recited in claim 1, wherein detecting the edges in the plurality of corresponding different resolution images further includes generating a corresponding plurality of detected edge maps.

8. The method as recited in claim 7, wherein comparing the corresponding edge parameters associated with the detected edges in the plurality of corresponding different resolution images further includes comparing corresponding edge amplitudes as provided in the plurality of detected edge maps to generate a result map.

9. The method as recited in claim 8, further comprising calculating a blur parameter based on the result map.

10. The method as recited in claim 9, wherein the blur parameter includes a blur percentage parameter.

11. The method as recited in claim 9, further comprising generating the plurality of corresponding different resolution images from a base image and determining if the base image is blurred based on a comparison of the blur parameter with at least one blur parameter threshold.

12. A computer-readable medium having computer-implementable instructions for performing acts comprising:

locating edges in a plurality of corresponding different resolution samples of an image; and

for each located edge, comparing corresponding edge parameters associated with the located edges in the plurality of corresponding different resolution samples to determine if the located edge is significantly blurred.

13. The computer-readable medium as recited in claim 12, wherein the corresponding edge parameters associated with the located edges in the plurality of corresponding different resolution samples include amplitudes associated with located edges.

14. The computer-readable medium as recited in claim 12, having further computer-implementable instructions for performing acts comprising:

providing a base image file having image data associated with the image; and

processing the base image to produce one or more corresponding different resolution samples of the image.

15. The computer-readable medium as recited in claim 14, wherein the plurality of corresponding different resolution samples includes the base image and at least one corresponding lower resolution sample.

16. The computer-readable medium as recited in claim 14, wherein the plurality of corresponding different resolution samples includes the base image, a second corresponding lower resolution sample, and a third corresponding lower resolution sample that is also lower in resolution than the second corresponding lower resolution sample.

17. The computer-readable medium as recited in claim 14, wherein the base image is a portion of a larger original image.

18. The computer-readable medium as recited in claim 12, wherein locating the edges in the plurality of corresponding different resolution samples further includes generating a corresponding plurality of detected edge maps.

19. The computer-readable medium as recited in claim 18, wherein comparing the corresponding edge parameters associated with the located edges in the plurality of corresponding different resolution samples further includes comparing amplitudes as provided in the plurality of detected edge maps to generate a result map.

20. The computer-readable medium as recited in claim 19, having further computer-implementable instructions for performing acts comprising calculating at least one blur parameter based on the result map.

21. The computer-readable medium as recited in claim 20, wherein the blur parameter includes a blur percentage.

22. The computer-readable medium as recited in claim 20, having further computer-implementable instructions for performing acts comprising:

creating the plurality of corresponding different resolution samples from a base image; and

determining if selected portions of the base image are blurred based on a comparison of the blur parameter with at least one threshold value.

23. An apparatus comprising:

an edge detector configured to detect edge transitions in a plurality of corresponding different resolution images;

an edge parameter comparator configured to compare corresponding edge parameters as detected by the edge detector; and

a blur calculator configured to determine at least one blur parameter based on comparison results as determined by the edge parameter comparator.

24. The apparatus as recited in claim 23, wherein the corresponding edge parameters include corresponding edge amplitudes associated with the detected edge transitions.

25. The apparatus as recited in claim 23, further comprising an image generator configured to generate the plurality of corresponding different resolution images based on an base image, and provide the plurality of corresponding different resolution images to the edge detector.

26. The apparatus as recited in claim 25, wherein the plurality of corresponding different resolution images includes the base image and at least one corresponding lower resolution image.

27. The apparatus as recited in claim 25, wherein the plurality of corresponding different resolution images includes the base image a second corresponding lower resolution image, and a third corresponding lower resolution image that is also lower in resolution than the second corresponding lower resolution image.

28. The apparatus as recited in claim 25, wherein the base image is a portion of a larger original image.

29. The apparatus as recited in claim 23, wherein the edge detector is further configured to generate a corresponding plurality of detected edge maps.

30. The apparatus as recited in claim 29, wherein the edge parameter comparator is further configured to compare corresponding edge amplitudes as provided in the plurality of detected edge maps to generate a result map.

31. The apparatus as recited in claim 30, wherein the blur calculator is further configured to calculate the at least one blur parameter based on the result map.

32. The apparatus as recited in claim 31, wherein the at least one blur parameter includes a blur percentage parameter.

33. The apparatus as recited in claim 25, further comprising a blur detector configured to determine if the base image is blurred based on a comparison of the at least one blur parameter with at least one blur parameter threshold.

34. The apparatus as recited in claim 23, wherein the apparatus is configured within logic and memory of a computer.