PS 给出的定义：
Enhance Per Channel Contrast：Maximizes the tonal range in each channel to produce a more dramatic correction.Because each channel is adjusted individually, Enhance Per Channel Contrast may remove
or introduce color casts.The Auto Levels command uses this algorithm.
简单来说，就是对R，G，B三个通道的动态范围分别进行拉伸。这个算法还要考虑一个 clipping percentage， 默认值是 0.1%。根据这个定义，可以先编写一个拉伸动态范围的函数：
（函数中默认图像的动态范围是 0-1）.
if x<x_min: y=0;
if x>x_max: y=1;
if x_min < x< x_max: y=(x-x_min)/(x_max-x_min);
function I_out=F_color(I, percent)
%%% the tonal range of the input image is 0-1.
[row, col]=size(I);
I_sort=sort(I(:));
I_out=I;
%%% based on the clipping percentage,
%%% compute the upper and lower boundaries
if (percent==0)
I_min=min(I_sort)
I_max=max(I_sort)
else
I_min=I_sort(floor(row*col*percent))
I_max=I_sort(floor(row*col*(1-percent)))
end
for i=1:row
for j=1:col
if(I(i,j)<I_min)
I_out(i,j)=I_min;
elseif(I(i,j)>I_max)
I_out(i,j)=1;
else
I_out(i,j)=(I(i,j)-I_min)*(1-I_min)/(I_max-I_min)+I_min;
end
end
end
对三个通道分别进行拉伸，可以得到最终调整后的图像。
clc;
clear all;
Image=imread('8.jpg');
Image=double(Image)/255;
imshow(Image);
R=Image(:,:,1);
G=Image(:,:,2);
B=Image(:,:,3);
percent=0.001;
Image_out=Image;
Image_out(:,:,1)=F_color(R, percent);
Image_out(:,:,2)=F_color(G, percent);
Image_out(:,:,3)=F_color(B, percent);
figure, imshow(Image_out);
原图：
调整后的图：
