Granted Patent B2

US 7,899,229 · App. 11/834,304 · Granted Mar 1, 2011

Abstract

Claims (45)

1. A method for detecting one or more motion effects in a diagnostic image, executed using a processor, comprising:

obtaining image data of the diagnostic image;

identifying at least one region of interest in the diagnostic image by applying a template with one or more predefined regions of interest to the image;

calculating the probability of motion blur within the at least one region of interest according to a motion-sensitive feature of the at least one region of interest; and

reporting the calculated probability for motion blur within the at least one region of interest.

2. The method of claim 1 further comprising arranging the image data according to a predetermined image orientation.

3. The method of claim 1 wherein the diagnostic image is a digital radiographic image.

4. The method of claim 1 wherein the motion-sensitive feature of the at least one region of interest is an edge feature.

5. The method of claim 1 wherein calculating the probability of motion blur comprises:

forming, from data within the region of interest, at least one edge image with respect to a predetermined direction;

obtaining a histogram of edge image values for the at least one edge image;

identifying one or more motion-sensitive features according to histogram data; and

evaluating the one or more identified motion-sensitive features to obtain a probability value for motion blur.

6. The method of claim 5 wherein one or more motion sensitive features are computed based on the mean local variation of edge images.

7. The method of claim 5 wherein one or more motion sensitive features are computed based on statistical measures of the variation of edge values.

8. The method of claim 5 wherein one or more motion sensitive features are computed based on an estimate of edge strength within a predetermined range in edge histograms.

9. The method of claim 5 wherein evaluating the one or more calculated image features to obtain a probability value for motion blur further comprises:

applying a trained classifier to assess the motion sensitive features; and

generating a probability value of motion blur according to results from the trained classifier.

10. The method of claim 1 wherein identifying at least one region of interest comprises:

assigning at least one point in the image as a seed;

evaluating statistical values of the corresponding features adjacent to the seed;

merging adjacent pixels satisfying preset requirements with the seed to form the region of interest; and

repeating the steps of evaluating and merging until a predetermined requirement is met.

11. The method of claim 1 wherein reporting at least one region of interest that exhibits motion blur comprises reporting a global probability of motion by combining probabilities of more than one region of interest in the diagnostic image.

12. The method of claim 1 wherein reporting calculated probability for motion blur within the at least one region of interest comprises reporting according to an operator-adjusted sensitivity value.

13. The method of claim 1 wherein reporting the calculated probability comprises displaying an image on a display monitor.

14. The method of claim 13 further comprising highlighting the at least one region of interest on the display monitor.

15. The method of claim 13 further comprising displaying a corresponding probability value for motion blur for the at least one region of interest.

16. The method of claim 13 wherein the displayed image is a first version of the image and further comprising displaying a second version of the image on the display monitor, wherein the first and second versions are processed differently.

17. The method of claim 13 further comprising providing operator controls to adjust image rendering.

18. The method of claim 13 further comprising providing operator controls to adjust magnification and roam.

19. The method of claim 13 wherein an outline color indicates a relative range of probability for motion blur.

20. The method of claim 13 further comprising providing an icon that indicates a probability value for motion blur in the at least one region of interest that displays.

21. The method of claim 1 further comprising directing the diagnostic image to another viewer.

22. The method of claim 1 further comprising providing an instruction to retake the image.

23. The method of claim 1 wherein reporting the calculated probability comprises generating a hardcopy print.

24. The method of claim 1 wherein reporting the calculated probability comprises recording a calculated value in a database.

25. The method of claim 24 wherein reporting the calculated probability further comprises storing coordinates of the region of interest in the database.

26. A method for detecting one or more motion effects in a diagnostic image, executed using a processor, comprising:

obtaining image data for the diagnostic image;

arranging the image data according to a predetermined image orientation;

identifying at least one region of interest in the diagnostic image by applying a template with one or more predefined regions of interest to the image;

calculating the probability of motion blur within the at least one region of interest according to one or more edge features within the at least one region of interest; and

reporting the calculated probability for motion blur within the at least one region of interest.

Assignments (12)