Method and system for processing to enhance digital images
View Patent ↗A system reads a digital image that includes a set of pixels. The system determines a distribution of colors of the pixels of the digital image. Also, the system analyzes the distribution to identify a range of colors of a background of the digital image. Further, the system identifies pixels whose colors are within the identified range, and the system modifies the identified pixels to have a different color.
1. A method for processing a digital image, comprising:
storing a digital image that includes a set of pixels;
determining a distribution of color values of the set of pixels of the digital image;
determining a minimum ink density value associated with the digital image, wherein the minimum ink density value is determined by:
analyzing the distribution to identify a first range of color values that are the lightest group of color values in the digital image,
analyzing the distribution to identify a second range of color values that are the next-to-lightest group of color values in the digital image, and
arriving at the minimum ink density value by analyzing the second range of color values, wherein the analysis of the second range of colors is based on a pixel count associated with an adjacent pair of color values within the second range of colors, and the adjacent pair of color values has a slope that is closest to zero within the second range of color values;
determining a darkest color value, wherein the darkest color value is determined by analyzing the distribution to identify the darkest color value with a non-zero pixel count;
determining an ink offset based on the darkest color value; and
for each pixel of the set of pixels of the digital image:
determining if a color value associated with the pixel is darker than the minimum ink density value and,
if the color value of the pixel is darker than the minimum ink density, adjusting the color value associated with the pixel by adding the ink offset to the color value, and
if the color value of the pixel is not darker than the minimum ink density, setting the color value of the pixel to a background color value.
2. The method of claim 1 , wherein the first range of colors values are concentrated adjacent to one another within the distribution according to frequency of occurrence.
3. The method of claim 1 , wherein the first range of color values are a continuous range of color values.
4. The method of claim 2 , wherein the first range of color values are identified by applying Gaussian curve-fitting to a set of candidate color values to identify two color values having the lowest pixel count within a best fitting Gaussian curve.
5. The method of claim 3 , wherein the second range of color values are concentrated adjacent to one another within the distribution according to frequency of occurrence and the second range of color values is a continuous range of color values.
6. The method of claim 1 , wherein the background color value is white.
7. A system for digital image processing, comprising:
a processor; and
a computer readable medium storing:
a digital image that includes a set of pixels, and
a set of instructions executable by the processor for:
determining a distribution of color values of the set of pixels of the digital image;
determining a minimum ink density value associated with the digital image, wherein the minimum ink density value is determined by:
analyzing the distribution to identify a first range of color values that are the lightest group of color values in the digital image,
analyzing the distribution to identify a second range of color values that are the next-to-lightest group of color values in the digital image, and
arriving at the minimum ink density value by analyzing the second range of color values, wherein the analysis of the second range of colors is based on a pixel count associated with an adjacent pair of color values within the second range of colors, and the adjacent pair of color values has a slope that is closest to zero within the second range of color values;
determining a darkest color value, wherein the darkest color value is determined by analyzing the distribution to identify the darkest color value with a non-zero pixel count;
determining an ink offset based on the darkest color value, and
for each pixel of the set of pixels of the digital image:
determining if a color value associated with the pixel is darker than the minimum ink density value and,
if the color value of the pixel is darker than the minimum ink density, adjusting the color value associated with the pixel by adding the ink offset to the color value, and
if the color value of the pixel is not darker than the minimum ink density, setting the color value of the pixel to a background color value.
8. The system of claim 7 , wherein the first range of colors values are concentrated adjacent to one another within the distribution according to frequency of occurrence.
9. The system of claim 7 , wherein the first range of color values are a continuous range of color values.
10. The system of claim 8 , wherein the first range of color values are identified by applying Gaussian curve-fitting to a set of candidate color values to identify two color values having the lowest pixel count within a best fitting Gaussian curve.
11. The system of claim 9 , wherein the second range of color values are concentrated adjacent to one another within the distribution according to frequency of occurrence and the second range of color values is a continuous range of color values.
12. The system of claim 7 , wherein the background color value is white.
13. A non-transitory computer readable medium, comprising instructions executable by a processor to:
store a digital image that includes a set of pixels;
determine a distribution of color values of the set of pixels of the digital image;
determine a minimum ink density value associated with the digital image, wherein the minimum ink density value is determined by:
analyzing the distribution to identify a first range of color values that are the lightest group of color values in the digital image,
analyzing the distribution to identify a second range of color values that are the next-to-lightest group of color values in the digital image, and
arriving at the minimum ink density value by analyzing the second range of color values, wherein the analysis of the second range of colors is based on a pixel count associated with an adjacent pair of color values within the second range of colors, and the adjacent pair of color values has a slope that is closest to zero within the second range of color values;
determine a darkest color value, wherein the darkest color value is determined by analyzing the distribution to identify the darkest color value with a non-zero pixel count;
determine an ink offset based on the darkest color value; and
for each pixel of the set of pixels of the digital image:
determine if a color value associated with the pixel is darker than the minimum ink density value and,
if the color value of the pixel is darker than the minimum ink density, adjusting the color value associated with the pixel by adding the ink offset to the color value, and
if the color value of the pixel is not darker than the minimum ink density, setting the color value of the pixel to a background color value.
14. The computer readable medium of claim 13 , wherein the first range of color values are concentrated adjacent to one another within the distribution according to frequency of occurrence.
15. The computer readable medium of claim 13 , wherein the first range of color values are a continuous range of color values.
16. The computer readable medium of claim 14 , wherein the first range of color values are identified by applying Gaussian curve-fitting to a set of candidate color values to identify two color values having the lowest pixel count within a best fitting Gaussian curve.
17. The computer readable medium of claim 15 , wherein the second range of color values are concentrated adjacent to one another within the distribution according to frequency of occurrence and the second range of color values is a continuous range of color values.
18. The computer readable medium of claim 13 , wherein the background color value is white.