Specular light shadow removal for image de-noising
AssigneeIntel Corporation
InventorMichael Kounavis
Life of this patent
Estimating the term…
Abstract
Specular light shadow removal is described for use in image de-noising. In one example a method includes placing a window on an image, determining a cumulative distribution function for the window, determining a destination histogram for the window, determining a cumulative distribution function for the destination histogram, replacing the intensity of a pixel with the smallest index for which the histogram distribution for the pixel is greater than the window distribution, repeating determining a cumulative distribution function, a destination histogram, and a cumulative distribution function and replacing the intensity for a plurality of windows of the image, and de-noising the image after repeating by applying a median filter to the image.
Claims20
A method comprising:
- placing a window on an image;
- determining a cumulative distribution function for the window;
- determining a destination histogram for the window;
- determining a cumulative distribution function for the destination histogram;
- replacing the intensity of a pixel with the smallest index for which the histogram distribution for the pixel is greater than the window distribution;
- repeating determining a cumulative distribution function, a destination histogram, and a cumulative distribution function and replacing the intensity for a plurality of windows of the image;
- and
- de-noising the image after repeating by applying a median filter to the image.
A computer-readable medium having instructions stored thereon that when operated on by the computer cause the computer to perform operations comprising:
- placing a window on an image;
- determining a cumulative distribution function for the window;
- determining a destination histogram for the window;
- determining a cumulative distribution function for the destination histogram;
- replacing the intensity of a pixel with the smallest index for which the histogram distribution for the pixel is greater than the window distribution;
- repeating determining a cumulative distribution function, a destination histogram, and a cumulative distribution function and replacing the intensity for a plurality of windows of the image;
- and
- de-noising the image after repeating by applying a median filter to the image.
A computing system comprising:
- a camera to capture an image;
- an image processor to place a window on the captured image, to determine a cumulative distribution function for the window, to determine a destination histogram for the window, to determine a cumulative distribution function for the destination histogram, to replace the intensity of a pixel with the smallest index for which the histogram distribution for the pixel is greater than the window distribution, to repeat determining a cumulative distribution function, a destination histogram, and a cumulative distribution function and replacing the intensity for a plurality of windows of the image, and to de-noise the image after repeating by applying a median filter to the image;
- and
- a vision system to recognize a gesture in the de-noised image.
Dependencies are inferred from the claim text.