System, method, and computer program for adjusting image contrast using parameterized cumulative distribution functions
A system and method are provided for optimizing histogram cumulative distribution function curves. In use, a first image is received and divided into two or more pixel regions. For at least one of the two or more pixel regions, a first histogram is computed, and based on the first histogram, at least one cumulative distribution function is computed for the at least one of the two or more pixel regions. Next, based on the at least one cumulative distribution function, two or more curve fit coefficients are extracted and interpolated. Further, an interpolated cumulative distribution function is created based on the interpolation and the interpolated cumulative distribution function is applied to the at least one of the two or more pixel regions.
1. A device, comprising:
a non-transitory memory storing instructions; and
one or more processors in communication with the non-transitory memory, wherein the one or more processors execute the instructions to:
receive a first image;
divide the first image into two or more pixel regions;
for at least one of the two or more pixel regions, compute a first histogram;
based on the first histogram, compute a first cumulative distribution function;
based on the first cumulative distribution function, extract:
a first curve fit coefficient,
a first point associated with the first curve fit coefficient,
a first angle associated with the first curve fit coefficient,
a second curve fit coefficient,
a second point associated with the second curve fit coefficient, and
a second angle associated with the second curve fit coefficient;
create an interpolated cumulative distribution function based on the first curve fit coefficient, the first point, the first angle, the second curve fit coefficient, the second point, and the second angle; and
apply the interpolated cumulative distribution function to the at least one of the two or more pixel regions.
2. The device of claim 1 , wherein the interpolated cumulative distribution function is applied by normalizing a distribution of pixel intensity for the at least one of the two or more pixel regions.
3. The device of claim 1 , wherein the one or more processors further execute the instructions to compute at least two cumulative distribution functions for the at least one of the two or more pixel regions.
4. The device of claim 3 , wherein the device is operable such that the at least two cumulative distribution functions are used to extract the first curve fit coefficient and the second curve fit coefficient.
5. The device of claim 1 , wherein the interpolated cumulative distribution function is applied according to an interpolation of weights applied to the at least one of the two or more pixel regions.
6. The device of claim 5 , wherein the interpolation of weights is applied horizontally.
7. The device of claim 5 , wherein the interpolation of weights is applied vertically.
8. The device of claim 1 , wherein the one or more processors further execute the instructions to compute a second histogram for a second of the two or more pixel regions.
9. The device of claim 8 , wherein the one or more processors further execute the instructions to:
based on the second histogram, compute at least one second cumulative distribution function for the second of the two or more pixel regions;
based on the at least one second cumulative distribution function, extract two or more second curve fit coefficients;
interpolate the second curve fit coefficients to create a second interpolated cumulative distribution function;
apply the second interpolated cumulative distribution function to the second of the two or more pixel regions.
10. The device of claim 1 , wherein the interpolated cumulative distribution function is applied by modifying a contrast over the at least one of the two or more pixel regions.
11. The device of claim 1 , wherein the interpolated cumulative distribution function is applied to a subset of the at least one of the two or more pixel regions.
12. The device of claim 1 , wherein the interpolated cumulative distribution function is used to remove artifacts from the at least one of the two or more pixel regions.
13. The device of claim 12 , wherein the artifacts include bilinear interpolation artifacts.
14. The device of claim 1 , wherein the device is operable such that the at least one of the two or more pixel regions is selected based on a pixel of interest.
15. The device of claim 14 , wherein the device is operable such that the pixel of interest is associated with an identified object.
16. The device of claim 15 , wherein the device is operable such that a priority associated with the identified object is predetermined.
17. A method, comprising:
receiving, using an image processor, a first image;
dividing the first image into two or more pixel regions;
for at least one of the two or more pixel regions, computing a first histogram;
based on the first histogram, computing a first cumulative distribution function;
based on the first cumulative distribution function, extracting:
a first curve fit coefficient,
a first point associated with the first curve fit coefficient,
a first angle associated with the first curve fit coefficient,
a second curve fit coefficient,
a second point associated with the second curve fit coefficient, and
a second angle associated with the second curve fit coefficient;
creating an interpolated cumulative distribution function based on the first curve fit coefficient, the first point, the first angle, the second curve fit coefficient, the second point, and the second angle; and
applying the interpolated cumulative distribution function to the at least one of the two or more pixel regions.
18. A computer program product comprising computer executable instructions stored on a non-transitory computer readable medium that when executed by a processor instruct the processor to:
receive a first image;
divide the first image into two or more pixel regions;
for at least one of the two or more pixel regions, compute a first histogram;
based on the first histogram, compute a first cumulative distribution function;
based on the first cumulative distribution function, extract:
a first curve fit coefficient,
a first point associated with the first curve fit coefficient,
a first angle associated with the first curve fit coefficient,
a second curve fit coefficient,
a second point associated with the second curve fit coefficient, and
a second angle associated with the second curve fit coefficient;
create an interpolated cumulative distribution function based on the first curve fit coefficient, the first point, the first angle, the second curve fit coefficient, the second point, and the second angle; and
apply the interpolated cumulative distribution function to the at least one of the two or more pixel regions.