METHOD AND PRODUCT FOR PROCESSING DIGITAL IMAGES

• US 20050213845A1
• Filed: 03/24/2004
• Published: 09/29/2005
• Est. Priority Date: 03/24/2004
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Lal, Rakesh Mohan, Avinash, Gopal B.
• Granted Patent: US 7,623,728 B2
• Time in Patent Office: Days
• US Class Current: 382/275
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/20012 Locally adaptive
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation

Abstract

A method and computer program product for processing a digital image is disclosed. A foreground region relating to an imaged object is estimated, a background region relating to other than the imaged object is estimated, and by using the image, the estimated foreground region and the estimated background region, a transition region disposed between the foreground region and the background region is calculated. The estimated foreground region, the estimated background region, and the calculated transition region, each include a separate set of pixels that may each be processed separately for suppressing pixel intensities in the estimated background region and improving image quality.

Claims

1. A method for processing a digital image, the method comprising:

estimating a foreground region relating to an imaged object;

estimating a background region relating to other than the imaged object; and

by using the image, the estimated foreground region and the estimated background region, calculating a transition region disposed between the foreground region and the background region;

wherein the estimated foreground region, the estimated background region, and the calculated transition region, each comprise a separate set of pixels that may each be processed separately for suppressing pixel intensities in the estimated background region and improving image quality.

2. The method of claim 1, wherein:

the estimating a foreground region comprises defining an initial foreground region as that region containing those pixels of the image meeting a first criterion; and

the estimating a background region comprises defining the background region as that region containing those pixels of the image meeting a second criterion.

3. The method of claim 2, wherein the first criterion comprises a pixel intensity greater than a first threshold.

4. The method of claim 2, wherein the second criterion comprises a pixel intensity less than a second threshold.

5. The method of claim 2, wherein the calculating a transition region comprises calculating the transition region as that region containing those pixels of the image meeting a third criterion.

6. The method of claim 5, wherein the third criterion comprises:

a pixel having a pixel intensity greater than the second threshold, a morphological connection to a foreground pixel, and a gradient magnitude that is within a gradient tolerance value of the gradient magnitude of the foreground pixel.

7. The method of claim 5, wherein the calculating a transition region further comprises:

iteratively calculating incremental transition regions, each having an incrementally larger gradient tolerance value, until a gradient tolerance value threshold is met or exceeded, wherein;

each incremental transition region is calculated to be that region containing pixels connected to a pixel of a previously calculated incremental transition region, having an intensity greater than the second threshold, and having a gradient magnitude that is within the incrementally larger gradient tolerance value of the gradient magnitude of the incremental transition region pixel to which it is connected.

8. The method of claim 7, wherein the calculating a transition region further comprises:

using a focus parameter to merge a defined number of the initial plus incremental transition regions into a single transition region.

9. The method of claim 8, further comprising:

defining an object region as the union of the initial foreground region and the single transition region, and performing at least one morphological operation on the object region.

10. The method of claim 9, further comprising:

defining a final foreground mask as the initial foreground region;

defining a final transition mask as the difference between the object region and the final foreground region; and

defining a final background mask as the remainder of the image.

11. The method of claim 8, further comprising:

suppressing pixel intensities in the background region by gradually reducing the intensity of background pixels to zero as a function of their distance from the object region.

12. The method of claim 11, wherein the function comprises a linear ramp function, an exponential function, a Gaussian function, a Hanning function, a Hamming function, any function for reducing a value with respect to distance, or any combination of functions comprising at least one of the foregoing functions.

13. The method of claim 5, further comprising:

defining an object region as the union of the initial foreground region and the initial transition region, and performing at least one morphological operation on the object region.

14. The method of claim 13, further comprising:

defining a final foreground mask as the initial foreground region;

defining a final transition mask as the difference between the object region and the final foreground region; and

defining a final background mask as the remainder of the image.

15. The method of claim 14, further comprising:

suppressing pixel intensities in the background region by gradually reducing the intensity of background pixels to zero as a function of their distance from the object region.

16. The method of claim 15, wherein the function comprises a linear ramp function, an exponential function, a Gaussian function, a Hanning function, a Hamming function, any function for reducing a value with respect to distance, or any combination of functions comprising at least one of the foregoing functions.

17. The method of claim 1, wherein the digital image is a digital image of a biological object obtained using MR imaging, CT imaging, Ultrasound imaging, X-ray imaging, or any combination comprising at least one of the foregoing imaging processes.

18. A computer program product for processing a digital image, the product comprising:

a storage medium, readable by a processing circuit, storing instructions for execution by the processing circuit for;

estimating a foreground region relating to an imaged object;

estimating a background region relating to other than the imaged object; and

by using the image, the estimated foreground region and the estimated background region, calculating a transition region disposed between the foreground region and the background region;

wherein the estimated foreground region, the estimated background region, and the calculated transition region, each comprise a separate set of pixels that may each be processed separately for suppressing pixel intensities in the estimated background region and improving image quality.

19. The product of claim 18, wherein:

the estimating a foreground region comprises defining an initial foreground region as that region containing those pixels of the image meeting a first criterion; and

the estimating a background region comprises defining the background region as that region containing those pixels of the image meeting a second criterion.

20. The product of claim 19, wherein the first criterion comprises a pixel intensity greater than a first threshold.

21. The product of claim 19, wherein the second criterion comprises a pixel intensity less than a second threshold.

22. The product of claim 21, wherein the calculating a transition region comprises calculating the transition region as that region containing those pixels of the image meeting a third criterion.

23. The product of claim 22, wherein the third criterion comprises:

a pixel having a pixel intensity greater than the second threshold, a morphological connection to a foreground pixel, and a gradient magnitude that is within a gradient tolerance value of the gradient magnitude of the foreground pixel.

24. The product of claim 23, further comprising instructions for execution by the processing circuit for:

defining an object region as the union of the initial foreground region and the initial transition region, and performing at least one morphological operation on the object region.

25. The product of claim 24, further comprising instructions for execution by the processing circuit for:

defining a final foreground mask as the initial foreground region;

defining a final transition mask as the difference between the object region and the final foreground region; and

defining a final background mask as the remainder of the image.

26. The product of claim 25, further comprising instructions for execution by the processing circuit for:

suppressing pixel intensities in the background region by gradually reducing the intensity of background pixels to zero as a function of their distance from the object region.

27. The product of claim 26, wherein the function comprises a linear ramp function, an exponential function, a Gaussian function, a Hanning function, a Hamming function, any function for reducing a value with respect to distance, or any combination of functions comprising at least one of the foregoing functions.

28. The product of claim 23, wherein the calculating a transition region further comprises:

iteratively calculating incremental transition regions, each having an incrementally larger gradient tolerance value, until a gradient tolerance value threshold is met or exceeded, wherein;

each incremental transition region is calculated to be that region containing pixels connected to a pixel of a previously calculated incremental transition region, having an intensity greater than the second threshold, and having a gradient magnitude that is within the incrementally larger gradient tolerance value of the gradient magnitude of the incremental transition region pixel to which it is connected.

29. The product of claim 28, wherein the calculating a transition region further comprises:

using a focus parameter to merge a defined number of the initial plus incremental transition regions into a single transition region.

30. The product of claim 18, wherein the digital image is a digital image of a biological object obtained using MR imaging, CT imaging, Ultrasound imaging, X-ray imaging, or any combination comprising at least one of the foregoing imaging processes.