Determining sharpness predictors for a digital image

• US 20060056731A1
• Filed: 09/10/2004
• Published: 03/16/2006
• Est. Priority Date: 09/10/2004
• Status: Active Grant

• Current Assignee: Monument Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Eastman Kodak Company
• Inventors: Enge, Amy D., Spaulding, Kevin E., Bouk, Theodore F.
• Granted Patent: US 7,764,844 B2
• Time in Patent Office: Days
• US Class Current: 382/286
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/20052 Discrete cosine transform [DCT]
• CPC Class Codes: G06T 2207/30144 Printing quality
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: H04N 19/60 using transform coding
• CPC Class Codes: H04N 19/85 using pre-processing or post-processing specially adapted for video compression

Abstract

A method for determining a sharpness predictor for an input digital image includes determining one or more image metrics by analyzing the input digital image; and determining the sharpness predictor from the one or more image metrics.

Claims

1. A method for determining a sharpness predictor for an input digital image comprising:

a) determining one or more image metrics by analyzing the input digital image; and

b) determining the sharpness predictor from the one or more image metrics.

2. The method of claim 1 wherein at least one of the image metrics is related to the spatial frequency content of the input digital image.

3. The method of claim 1 wherein the input digital image is an image captured using a digital camera.

4. The method of claim 1 wherein the input digital image is a color input digital image and one or more of the image metrics are determined from a luminance signal computed from the color input digital image.

5. The method of claim 2 wherein the determination of one or more of the image metrics includes computing blocks of discrete cosine transform coefficients by applying discrete cosine transforms to blocks of the input digital image.

6. The method of claim 5 includes the step of computing image statistics for the blocks of discrete cosine transform coefficients.

7. The method of claim 6 wherein the computation of the image statistics includes computing a centroid for the blocks of discrete cosine transform coefficients.

8. The method of claim 6 wherein the computation of the image statistics includes computing sums for the blocks of discrete cosine transform coefficients.

9. The method of claim 6 wherein blocks of discrete cosine transform coefficients failing to meet a threshold criterion are excluded from the computation of the image statistics.

10. The method of claim 5 wherein the step of applying discrete cosine transforms to blocks of the input digital image is applied as part of an image compression operation.

11. The method of claim 1 wherein at least one of the image metrics is determined from compressed digital image data determined using an image compression operation.

12. The method of claim 1 wherein the determination of one or more of the image metrics includes the step of determining the number of image pixels darker than a specified threshold.

13. The method of claim 1 wherein the determination of one or more of the image metrics includes the step of determining the number of image pixels lighter than a specified threshold.

14. The method of claim 1 wherein the image metrics are determined from a subset of the input digital image.

15. The method of claim 14 wherein the subset of the input digital image is extracted from the center of the input digital image.

16. The method of claim 14 wherein the subset of the input digital image corresponds to a main subject region of the input digital image.

17. The method of claim 16 wherein an automatic main subject detection algorithm is used to identify the main subject region of the input digital image.

18. The method of claim 14 wherein the subset of the input digital image is interactively specified by a user.

19. The method of claim 1 wherein the sharpness predictor is determined by computing a weighted summation of the one or more image metrics.

20. The method of claim 1 wherein the sharpness predictor is determined by computing a weighted sum of functions of the one or more image metrics.

21. The method of claim 1 further including the step of using the sharpness predictor to estimate whether the quality of the input digital image is sufficient for a particular usage.

22. The method of claim 20 wherein the usage is producing a reflection print.

23. The method of claim 1 further including the step of using the sharpness predictor to present a recommended image usage to a user via a user interface.

24. The method of claim 1 further including the step of using the sharpness predictor as a control parameter for a subsequent image processing operation.

25. The method of claim 24 wherein weighting coefficients used to weight the two or more image metrics in the weighted summation are determined by using a statistical analysis to correlate values of the two or more image metrics and subjectively determined image sharpness values for a set of test images.

26. The method of claim 1 wherein the sharpness predictor is determined by combining two or more image metrics using a neural network calculation, where the neural network has been trained using subjectively determined image sharpness values for a set of test images.

27. The method of claim 1 wherein the step of determining the sharpness predictor further includes using one or more additional sharpness metrics determined from image capture parameters.

28. The method of claim 27 wherein the image capture parameters include an exposure time parameter, a lens aperture parameter, a flash-fired parameter, or combinations thereof.

29. A computer program product, comprising a computer readable storage medium for practicing the method according to claim 1.