Flexible region of interest color processing for cameras

1. An apparatus configured for image processing, the apparatus comprising:

a memory configured to store a first image captured by an image sensor of a camera module; and

one or more processors in communication with the memory, the one or more processors configured to:

receive the first image;

determine one or more first automatic white balance (AWB) parameters for the first image;

determine one or more second AWB parameters for a region-of-interest (ROI) of the first image;

apply the one or more first AWB parameters to at least a portion of one or more of the first image or a second image;

divide the ROI into a grid including a plurality of rectangular regions; and

apply a lens shading correction grid gain to pixels in each respective rectangular region of the plurality of rectangular regions in the grid, wherein the lens shading correction grid gain is based on the second AWB parameters, wherein to apply the lens shading correction grid gain, the one or more processors are configured to:

determine a local adjustment gain (LAG) from the second AWB Parameters;

determine a respective x-direction weight (WeightX) for each respective rectangular region of the plurality of rectangular regions;

determine a respective y-direction weight (WeightY) for each respective rectangular region of the plurality of rectangular regions; and

apply the lens shading correction grid gain in each respective rectangular region of the plurality of rectangular regions in the grid as a function of WeightX*WeightY*LAG.

2. The apparatus of claim 1 , wherein the one or more processors are further configured to:

apply the one or more first AWB parameters to one or more of the first image or the second image; and

adjust the ROI in one or more of the first image or the second image based on the one or more second AWB parameters.

3. The apparatus of claim 2 , wherein the ROI includes skin of a person.

4. The apparatus of claim 3 , wherein the one or more processors are further configured to detect a face.

5. The apparatus of claim 4 , wherein the one or more processors are further configured to detect an area of the skin in the face.

6. The apparatus of claim 5 , wherein to detect the area of the skin in the face, the one or more processors are configured to detect the area of the skin in the face using one or more segmentation techniques, wherein the one or more segmentation techniques include one or more of artificial intelligence-based skin detection or skin chroma filtering.

7. The apparatus of claim 5 , wherein to adjust the ROI in one or more of the first image or the second image based on the one or more second AWB parameters, the one or more processors are configured to adjust the area of the skin in the face of one or more of the first image or the second image based on the one or more second AWB parameters.

8. The apparatus of claim 1 , wherein the one or more first AWB parameters or the one or more second AWB parameters include one or more of an AWB gain, a correlated color temperature (CCT), or a color correction matrix (CCM).

9. The apparatus of claim 1 , wherein to determine the one or more second AWB parameters for the ROI of the first image, the one or more processors are further configured to determine the one or more second AWB parameters for the ROI of the first image based in part on the one or more first AWB parameters.

10. The apparatus of claim 1 , wherein to determine the one or more second AWB parameters for the ROI of the first image, the one or more processors are further configured to determine the one or more second AWB parameters for the ROI of the first image based only on pixel values in the ROI.

11. The apparatus of claim 1 , wherein to determine the one or more first AWB parameters for the first image, the one or more processors are further configured to determine the one or more first AWB parameters for the first image using a gray-world technique.

12. The apparatus of claim 1 , further comprising the camera module configured to capture the first image.

13. The apparatus of claim 1 , wherein the camera module is part of a mobile telephone.

14. The apparatus of claim 1 , wherein the one or more processors are configured to:

determine the respective x-direction weight (WeightX) based on a first ratio of an x-dimension of the respective rectangular region relative to the ROI; and

determine the respective y-direction weight (WeightY) based on a second ratio of a y-dimension of the respective rectangular region relative to the ROI.

15. A method for image processing, the method comprising:

receiving a first image;

determining one or more first automatic white balance (AWB) parameters for the first image;

determining one or more second AWB parameters for a region-of-interest (ROI) of the first image;

applying the one or more first AWB parameters to at least a portion of one or more of the first image or a second image;

dividing the ROI into a grid including a plurality of rectangular regions; and

applying a lens shading correction grid gain to pixels in each respective rectangular region of the plurality of rectangular regions in the grid, wherein the lens shading correction grid gain is based on the second AWB parameters, wherein applying the lens shading correction grid gain comprises:

determining a local adjustment gain (LAG) from the second AWB parameters;

determining a respective x-direction weight (WeightX) for each respective rectangular region of the plurality of rectangular regions;

determining a respective y-direction weight (WeightY) for each respective rectangular region of the plurality of rectangular regions; and

applying the lens shading correction grid gain in each respective rectangular region of the plurality of rectangular regions in the grid as a function of WeightX*WeightY*LAG.

16. The method of claim 15 , further comprising:

applying the one or more first AWB parameters to one or more of the first image or the second image; and

adjusting the ROI in one or more of the first image or the second image based on the one or more second AWB parameters.

17. The method of claim 16 , wherein the ROI includes skin of a person.

18. The method of claim 17 , further comprising detecting a face.

19. The method of claim 18 , further comprising detecting an area of the skin in the face.

20. The method of claim 19 , wherein detecting the area of the skin in the face comprises detecting the area of the skin in the face using one or more segmentation techniques, wherein the one or more segmentation techniques include one or more of artificial intelligence-based skin detection or skin chroma filtering.

21. The method of claim 19 , wherein adjusting the ROI in one or more of the first image or the second image based on the one or more second AWB parameters comprises adjusting the area of the skin in the face of one or more of the first image or the second image based on the one or more second AWB parameters.

22. The method of claim 15 , wherein the one or more first AWB parameters or the one or more second AWB parameters include one or more of an AWB gain, a correlated color temperature (CCT), or a color correction matrix (CCM).

23. The method of claim 15 , wherein determining the one or more second AWB parameters for the ROI of the first image comprises determining the one or more second AWB parameters for the ROI of the first image based in part on the one or more first AWB parameters.

24. The method of claim 15 , wherein determining the one or more second AWB parameters for the ROI of the first image comprises determining the one or more second AWB parameters for the ROI of the first image based only on pixel values in the ROI.

25. The method of claim 15 , wherein determining the one or more first AWB parameters for the first image comprises determining the one or more first AWB parameters for the first image using a gray-world technique.

26. The method of claim 15 , further comprising:

determining the respective x-direction weight (WeightX) based on a first ratio of an x-dimension of the respective rectangular region relative to the ROI; and

determining the respective y-direction weight (WeightY) based on a second ratio of a y-dimension of the respective rectangular region relative to the ROI.

27. A non-transitory computer-readable storage medium storing instructions that, when executed, causes one or more processors to:

receive a first image;

determine one or more first automatic white balance (AWB) parameters for the first image;

determine one or more second AWB parameters for a region-of-interest (ROI) of the first image;

apply the one or more first AWB parameters to at least a portion of one or more of the first image or a second image;

divide the ROI into a grid including a plurality of rectangular regions; and

apply a lens shading correction grid gain to pixels in each respective rectangular region of the plurality of rectangular regions in the grid, wherein the lens shading correction grid gain is based on the second AWB parameters, wherein to apply the lens shading correction grid gain, the instructions further cause the one or more processors to:

determine a local adjustment gain (LAG) from the second AWB parameters;

determine a respective x-direction weight (WeightX) for each respective rectangular region of the plurality of rectangular regions;

determine a respective y-direction weight (WeightY) for each respective rectangular region of the plurality of rectangular regions; and

apply the lens shading correction grid gain in each respective rectangular region of the plurality of rectangular regions in the grid as a function of WeightX*WeightY*LAG.

28. The non-transitory computer-readable storage medium of claim 27 , wherein instructions further cause the one or more processors to:

apply the one or more first AWB parameters to one or more of the first image or the second image; and

adjust the ROI in one or more of the first image or the second image based on the one or more second AWB parameters.

29. The non-transitory computer-readable storage medium of claim 28 , wherein the ROI includes skin of a person.

30. The non-transitory computer-readable storage medium of claim 29 , wherein the instructions further cause the one or more processors to detect a face.

31. The non-transitory computer-readable storage medium of claim 30 , wherein the instructions further cause the one or more processors to detect an area of the skin in the face.

32. The non-transitory computer-readable storage medium of claim 31 , wherein to detect the area of the skin in the face, the instructions further cause the one or more processors to detect the area of the skin in the face using one or more segmentation techniques, wherein the one or more segmentation techniques include one or more of artificial intelligence-based skin detection or skin chroma filtering.

33. The non-transitory computer-readable storage medium of claim 31 , wherein to adjust the ROI in one or more of the first image or the second image based on the one or more second AWB parameters, the instructions further cause the one or more processors to adjust the area of the skin in the face of one or more of the first image or the second image based on the one or more second AWB parameters.

34. The non-transitory computer-readable storage medium of claim 27 , wherein the one or more first AWB parameters or the one or more second AWB parameters include one or more of an AWB gain, a correlated color temperature (CCT), or a color correction matrix (CCM).

35. The non-transitory computer-readable storage medium of claim 27 , wherein to determine the one or more second AWB parameters for the ROI of the first image, the instructions further cause the one or more processors to determine the one or more second AWB parameters for the ROI of the first image based in part on the one or more first AWB parameters.

36. The non-transitory computer-readable storage medium of claim 27 , wherein to determine the one or more second AWB parameters for the ROI of the first image, the instructions further cause the one or more processors to determine the one or more second AWB parameters for the ROI of the first image based only on pixel values in the ROI.

37. The non-transitory computer-readable storage medium of claim 27 , wherein to determine the one or more first AWB parameters for the first image, the instructions further cause the one or more processors to determine the one or more first AWB parameters for the first image using a gray-world technique.

38. The -transitory computer-readable storage medium of claim 27 , wherein the instructions further cause the one or more processors to:

determine the respective x-direction weight (WeightX) based on a first ratio of an x-dimension of the respective rectangular region relative to the ROI; and

determine the respective y-direction weight (WeightY) based on a second ratio of a y-dimension of the respective rectangular region relative to the ROI.