Back to results
US 7,609,908 B2Granted
Method for adjusting the brightness of a digital image utilizing belief values
AssigneeEastman Kodak Company
InventorsJiebo Luo, Michael W. Dupin, Andrew C. Gallagher
Life of this patent
Estimating the term…
Abstract
A method of processing a digital image, including the steps of: assigning belief values to pixels in the digital image, wherein the belief values are proportional to a belief that the pixels are associated with human skin; calculating a brightness adjustment amount based on a statistic of the pixels with belief values exceeding a threshold and the assigned belief values of the pixels; and applying the brightness adjustment amount to the digital image to produce a processed digital image having improved overall brightness.
Claims21
A method of processing a digital image, comprising the steps of:
- a) assigning belief values according to instructions stored in a computer readable medium to pixels in the digital image, the belief values are subject to:
- (i) detecting a probability of both human skin color pixels and non-skin color pixels in the digital image and (ii) computing a geometric feature for spatially contiguous regions of skin-colored pixels, wherein the belief values are proportional to a belief that the skin color and non-skin color pixels are associated with human skin;
- b) ascertaining an image dependant adaptive skin probability threshold using both the human skin color pixels and the non-skin color pixels having desired gradient values;
- c) calculating a brightness adjustment amount based on a statistic of the pixels with belief values exceeding the skin probability threshold and the assigned belief values of the pixels;
- and
- d) applying the brightness adjustment amount to the digital image to produce a processed digital image having improved overall brightness.
3 more elements
A method of processing a digital image, comprising the steps of:
- a) assigning a probability value to skin-colored pixels and non-skin-colored pixels in the digital image according to instructions stored in a computer readable medium;
- b) producing a skin probability map for the image according to the probability value for each of the skin-colored pixels and non-skin-colored pixels in the digital image;
- c) determining gradient values for both the skin and non-skin colored pixels in the digital image;
- d) determining a variable skin probability threshold for the digital image according to selected gradient values of both skin and non-skin colored pixels in the digital image;
- e) extracting spatially contiguous regions of skin-colored pixels;
- f) producing a main subject skin belief map of belief values, wherein the belief values are calculated from the probability values of both the skin colored pixels and the non-skin colored pixels, the belief values indicate a belief in each extracted skin-colored region being pan of a main human subject, wherein the main subject skin belief map indicates skin-colored regions, in terms of location and the belief value, proportional to the belief that the skin-colored region is associated with the main human subject, having skin pixels, and located in the image;
- g) calculating a brightness adjustment amount based on a statistic of the detected skin-colored pixels and the belief values of such pixels;
- and
- h) applying the brightness adjustment amount to the digital image to produce a processed digital image having improved overall brightness.
6 more elements
A method of processing a digital image, comprising the steps of:
- a) assigning belief values according to instructions stored in a computer readable medium to pixels in the digital image, the belief values are subject to:
- (i) detecting a probability of human skin color pixels and non-skin color pixels for each pixel in the digital image and (ii) computing a geometric feature for spatially contiguous regions of skin-colored pixels, wherein the belief values are proportional to a belief that the human skin color pixels and non-skin color pixels are associated with human skin;
- b) calculating a brightness adjustment amount based on a statistic of the pixels with belief values exceeding an adaptive skin probability threshold and the assigned belief values of the pixels;
- c) applying the brightness adjustment amount to the digital image to produce a processed digital image having improved overall brightness;
- and
- d) customizing the adaptive skin probability threshold for the digital image by using an image-dependent adaptive thresholding algorithm dependent on the gradient of both the skin color pixels and the non-skin color pixels in the digital image.
3 more elements
Dependencies are inferred from the claim text.