Matlab底层源码实现图像动态二值化

理论

通常情况下，为了算法的稳定性，图像处理算法需要具有自适应调节阈值并进一步阈值分割，这里给出一种图像动态二值化的图像预处理算法，并在最后给出图像处理的效果。

Matlab源代码

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%动态二值化
%Author:Zhu
%时间：2022.6
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
clc;
image = imread("E:\\1.jpg");
image_matrix=image(:,:,1);
image_matrix=double(image_matrix);
[height,width,channels]=size(image);

%迭代阈值
threshold1 = 127;
threshold2 = 0;

%临时变量
temp1=0;
temp2=0;
temp3=0;
temp4=0;

%直方图统计
gray_map = zeros(1,256);
 for i=1:height
      for j=1:width
           T = image_matrix(i,j)+1;
           %灰度统计计数
           gray_map(T)=gray_map(T)+1;
      end
 end
 
while(1)
    %计算下一个迭代阈值
    for i=1:threshold1
        temp1=temp1+gray_map(i)*i;
        temp2=temp2+gray_map(i);
    end
    for i=threshold1:256
        temp3=temp1+gray_map(i)*i;
        temp4=temp2+gray_map(i);
    end
    
    threshold2 =(temp1/temp2+temp3/temp4)/2;
    threshold2=ceil(threshold2);
    %看迭代结果是否收敛
    if(threshold1==threshold2)
        threshold1=ceil(threshold1);
        break;
    else
        threshold1 = threshold2;
    end
end

%对各像素进行灰度转换
for i =1:height
    for j=1:width
        currentPixel = image_matrix(i,j);
        if(currentPixel<threshold1)
            currentPixel = 0;
        else
            currentPixel = 255;
        end
        image_matrix(i,j)=currentPixel;
    end
end

%显示图
image_out = uint8(image_matrix);
subplot(1,2,1);
imshow(image);
subplot(1,2,2);
imshow(image_out);

实现效果