图像预处理——matlab

参考此书：数字图像处理与机器视觉，第二版，张铮

—————————————————————————————————————
%图像预处理
RGBIm = imread(‘lena.jpg’);%读入图片
GRAYImage = rgb2gray(RGBIm);%图像灰度转换
threshold = graythresh(GRAYImage);%阈值
BW = im2bw(RGBIm,threshold);%二值化图像
imshow(BW );
—————————————————————————————————————

%%
%图像反转
RGBIm = imread(‘lena.jpg’);%读入图片
doubleimage = double(RGBIm);
doubleimage = -doubleimage +256-1;
H = uint8(doubleimage);
subplot(1,2,1);imshow(doubleimage);
subplot(1,2,2);imshow(H);

—————————————————————————————————————

%%
%直方图均衡
RGBIm = imread(‘lena.jpg’);%读入图片
gray = rgb2gray(RGBIm);
figure;
subplot(2,2,1);imshow(gray);
subplot(2,2,2);imhist(gray);%获得直方图
histIm = histeq(gray);%直方图均衡后的图片
subplot(2,2,3);imshow(histIm);
subplot(2,2,4);imhist(histIm);%获得直方图

—————————————————————————————————————

%%
%线性平滑滤波器
RGBIm = imread(‘lena.jpg’);%读入图片
gray = rgb2gray(RGBIm);
noiseIm = imnoise(gray,‘salt & pepper’,0.02);%添加椒盐噪声
K1 = filter2(fspecial(‘average’,3),noiseIm)/255; %进行33模板平滑滤波
K2 = filter2(fspecial(‘average’,5),noiseIm)/255; %进行55模板平滑滤波
%K3 = filter2(fspecial(‘average’,7),noiseIm)/255;%进行77模板平滑滤波
%K4 = filter2(fspecial(‘average’,9),noiseIm)/255;%进行99模板平滑滤波
K3 = filter2(fspecial(‘gaussian’),noiseIm)/255; %进行gaussian滤波
K4 = filter2(fspecial(‘prewitt’),noiseIm)/255; %用于边缘增强，大小为【3 3】，无参数
figure;
subplot(2,3,1);imshow(RGBIm);title(‘原始图像’);
subplot(232);imshow(noiseIm);title(‘添加椒盐噪声’);
subplot(233),imshow(K1);title(‘33模板平滑滤波’);
subplot(234),imshow(K2);title('55模板平滑滤波’);
subplot(235),imshow(K3);title(‘高斯滤波’);
subplot(236),imshow(K4);title(‘prewitt滤波’);

—————————————————————————————————————

%%
%中值滤波器
RGBIm = imread(‘lena.jpg’);%读入图片
gray = rgb2gray(RGBIm);
noiseIm = imnoise(gray,‘salt & pepper’,0.02);
K3 = medfilt2(noiseIm);%进行33模板中值滤波
K5 = medfilt2(noiseIm,[5,5]);%进行55模板中值滤波
K7 = medfilt2(noiseIm,[7,7]);%进行77模板中值滤波
K9 = medfilt2(noiseIm,[9,9]);%进行99模板中值滤波
figure;
subplot(231);imshow(RGBIm);title(‘原始图片’);
subplot(232);imshow(noiseIm);title(‘添加椒盐图片’);
subplot(233);imshow(K3);title(‘33模板中值滤波’);
subplot(234);imshow(K5);title('55模板中值滤波’);
subplot(235);imshow(K7);title(‘77模板中值滤波’);
subplot(236);imshow(K9);title('99模板中值滤波’);

—————————————————————————————————————

%%
%Sobel算子和拉普拉斯算子
RGBIm = imread(‘lena.jpg’);
gray = rgb2gray(RGBIm);
threshold = graythresh(gray);%阈值
BW = im2bw(RGBIm,threshold);

%选择sobel算子,用于边缘提取
fs_sobel = fspecial(‘sobel’);
SobelIm = filter2(fs_sobel,BW);%卷积运算

%拉普拉斯算子,默认值0.2
% h = [0 1 0,1 -4 1,0 1 0];
%laIm = conv2(BW,unit8(h),‘same’);
fs_lap = fspecial(‘laplacian’,0.7);
LapIm = filter2(fs_lap,BW);

%梯度算子检测边缘
roIm = edge(BW,‘roberts’);
soIm = edge(BW,‘sobel’);
prIm = edge(BW,‘prewitt’);

%log算子检测边缘
logIm = edge(BW,‘log’);
%canny算子
canIm = edge(BW,‘canny’);

figure;
subplot(241);imshow(RGBIm);title(‘原始图片’);
subplot(242);imshow(SobelIm);title(‘sobel锐化图像’);
subplot(243);imshow(roIm);title(‘laplacian检测边缘’);
subplot(244);imshow(soIm);title(‘roberts检测边缘’);
subplot(245);imshow(prIm);title(‘sobel检测边缘’);
subplot(246);imshow(LapIm);title(‘prewitt检测边缘’);
subplot(247);imshow(logIm);title(‘log检测边缘’);
subplot(248);imshow(canIm);title(‘canny检测边缘’);

—————————————————————————————————————

%%
%边界跟踪（bwtraceboundary函数）
RGBIm = imread(‘lena.jpg’);
gray = rgb2gray(RGBIm);
threshold = graythresh(gray);%使用此函数找到最佳阈值
BW = im2bw(gray,threshold);%使用此阈值将图像转化为二值图

dim = size(BW);
col = round(dim(2)/2)+90;%设定一个列坐标
row = find(BW(:,col),1);%在该列中找到第一个不为0的像素坐标
connectivity = 8;%8联通方式
num_points = 180;%设定曲线最长值
%contour中保存的是所有点的坐标
contour = bwtraceboundary(BW,[row,col],‘N’,connectivity,num_points);%使用该函数找到所有以改点为起点的曲线

figure;
%subplot(131);imshow(RGBIm);title(‘原始图片’);
%subplot(132);imshow(gray);title(‘二值化图片’);
%subplot(133);plot(contour(:,2),contour(:,1),‘g’,‘LineWidth’,2);title(‘原始图片’);
imshow(BW);title(‘二值化图像’);
figure;
imshow(RGBIm);hold on;
plot(contour(:,2),contour(:,1),‘g’,‘LineWidth’,2);title(‘原始图片’);title(‘边界跟踪图像’);

—————————————————————————————————————

%%
%Hough变换
RGBIm = imread(‘lena.jpg’);
gray = rgb2gray(RGBIm);
threashold = graythresh(gray);%阈值
BW = im2bw(gray,threashold);%二值化图像
figure;
subplot(221);imshow(gray);title(‘二值化图像’);
preIm = edge(BW,‘prewitt’);
[H,T,R] = hough(preIm);
subplot(222);imshow(H,[],‘XData’,T,‘YData’,R,‘InitialMagnification’,‘fit’);
xlabel(’\theta’), ylabel(’\rho’);
axis on,axis square,hold on;
P=houghpeaks(H,3);
x = T(P(:,2));
y = R(P(:,1));
plot(x,y,‘s’,‘color’,‘white’);%标出极值点
lines = houghlines(preIm,T,R,P);%提取线段
subplot(223);imshow(RGBIm),hold on;
for k=1:length(lines)
xy = [lines(k).point1;lines(k).point2];
plot(xy(:,1),xy(:,2),‘LineWidth’,2,‘Color’,‘green’);%画出线段
plot(xy(1,1),xy(1,2),‘x’,‘LineWidth’,2,‘Color’,‘yellow’);%起点
plot(xy(2,1),xy(2,2),‘x’,‘LineWidth’,2,‘Color’,‘red’);%终点
end

—————————————————————————————————————

%%
%直方图阈值法
RGBIm = imread(‘lena.jpg’);
gray = rgb2gray(RGBIm);
figure;
subplot(221);imshow(gray);title(‘灰度图像’);
axis([50,250,50,200]);axis on;grid on;
[m,n] = size(gray);
GP = zeros(1,256);%预创建存放灰度出现概率的向量
for k=0:255
GP(k+1) = length(find(gray == k))/(m*n);%计算每级灰度出现的概率，将其存放在GP中相应的位置
end
subplot(222);bar(0:255,GP,‘g’);title(‘灰度直方图’);%bar创建条形图
xlabel(‘灰度值’);ylabel(‘出现概率’);
BW1 = im2bw(RGBIm,150/255);
subplot(223);imshow(BW1);title(‘阈值150的分割图像’);
axis([50,250,50,200]);grid on;axis on;
BW2 = im2bw(RGBIm,200/255);
subplot(224);imshow(BW2);title(‘阈值200的分割图像’);
axis([50,250,50,200]);grid on;axis on;

—————————————————————————————————————

%%
%自动阈值法：Otsu法
RGBIm = imread(‘lena.jpg’);
level = graythresh(RGBIm);%在这个函数中，是使用最大类间方差法找到图片的一个合适的阈值
BW = im2bw(RGBIm,level);
subplot(121);imshow(RGBIm);title(‘原始图像’);
axis([50,250,50,200]);axis on;grid on;
subplot(122);imshow(BW);title(‘Otsu法阈值分割图像’);
axis([50,250,50,200]);axis on;grid on;

—————————————————————————————————————

%%
%膨胀操作
RGBIm = imread(‘lena.jpg’);
gray = rgb2gray(RGBIm);
subplot(221);imshow(RGBIm);title(‘原始图像’);
axis([50,250,50,200]);axis on;grid on;
subplot(222);imshow(gray);title(‘灰度图像’);
axis([50,250,50,200]);axis on;grid on;
se = strel(‘disk’,1);%生成圆形结构元素
I2 = imdilate(gray,se);%用生成的结构元素对图像进行膨胀
subplot(223);imshow(I2);title(‘膨胀后的图像’);
axis([50,250,50,200]);axis on;grid on;

—————————————————————————————————————

%%
%腐蚀操作
RGBIm = imread(‘lena.jpg’);
gray = rgb2gray(RGBIm);
subplot(221);imshow(RGBIm);title(‘原始图像’);
axis([50,250,50,200]);axis on;grid on;
subplot(222);imshow(gray);title(‘灰度图像’);
axis([50,250,50,200]);axis on;grid on;
se = strel(‘disk’,1);%生成圆形结构元素
I2 = imerode(gray,se);%用生成的结构元素对图像进行膨胀
subplot(223);imshow(I2);title(‘腐蚀后的图像’);
axis([50,250,50,200]);axis on;grid on;

—————————————————————————————————————

%%
%开启和闭合操作
RGBIm = imread(‘lena.jpg’);
gray = rgb2gray(RGBIm);
subplot(221);imshow(RGBIm);title(‘原始图像’);
axis([50,250,50,200]);axis on;grid on;
subplot(222);imshow(gray);title(‘灰度图像’);
axis([50,250,50,200]);axis on;grid on;
se = strel(‘disk’,1);%采用半径为1的圆作为结构元素
I2 = imopen(gray,se);%开启操作
I3 = imclose(gray,se);%闭合操作
subplot(2,2,3),imshow(I2);title(‘开启运算后图像’);
axis([50,250,50,200]);axis on;
subplot(2,2,4),imshow(I3);title(‘闭合运算后图像’);
axis([50,250,50,200]);axis on;

—————————————————————————————————————

%%
%开闭组合操作
I=imread(‘lena.jpg’);
subplot(3,2,1),imshow(I);title(‘原始图像’);
axis([50,250,50,200]);axis on;
I1=rgb2gray(I);
subplot(3,2,2),imshow(I1);title(‘灰度图像’);
axis([50,250,50,200]);axis on;
se=strel(‘disk’,1);
I2=imopen(I1,se);
I3=imclose(I1,se);
subplot(3,2,3),imshow(I2);title(‘开启运算后图像’);axis([50,250,50,200]);axis on;
subplot(3,2,4),imshow(I3);title(‘闭合运算后图像’);axis([50,250,50,200]);axis on;
se=strel(‘disk’,1);
I4=imopen(I1,se);
I5=imclose(I4,se);
subplot(3,2,5),imshow(I5); title(‘开—闭运算图像’);axis([50,250,50,200]);axis on;
I6=imclose(I1,se);
I7=imopen(I6,se);
subplot(3,2,6),imshow(I7); title(‘闭—开运算图像’);axis([50,250,50,200]);axis on;

—————————————————————————————————————

%%
%形态学边界提取
I=imread(‘lena.jpg’);
subplot(1,3,1),imshow(I);title(‘原始图像’);axis([50,250,50,200]);grid on;axis on;
BW = im2bw(I);
subplot(1,3,2),imshow(I1);title(‘二值化图像’);axis([50,250,50,200]);grid on; axis on;
I2=bwperim(BW); %获取区域的周长
subplot(1,3,3),imshow(I2);title(‘边界周长的二值图像’);
axis([50,250,50,200]);grid on;axis on;

—————————————————————————————————————

%%
%形态学骨架提取
I=imread(‘lena.jpg’);
subplot(2,2,1),imshow(I);
title(‘原始图像’);axis([50,250,50,200]);axis on;
BW=im2bw(I);
subplot(2,2,2),imshow(BW);title(‘二值图像’);axis([50,250,50,200]);axis on;
I2=bwmorph(BW,‘skel’,1);%骨骼化图像
subplot(2,2,3),imshow(I2);title(‘1次骨架提取’);axis([50,250,50,200]);axis on;
I3=bwmorph(BW,‘skel’,3);
subplot(2,2,4),imshow(I3);title(‘2次骨架提取’);axis([50,250,50,200]);axis on;