计算机视觉实验5形态学滤波实验报告

Experiment 4：Thresholding & mathematical morphology
王影电子1203班学号：1210910322
Ⅰ. Aim
The aim of this laboratory session is to learn to deal with image data by Matlab. By the end of this session, you should be able to perform image preprocessing of thresholding and mathematical morphology.
Ⅱ. Knowledge required in the Experiment
ⅰ.You are supposed to have learned the basic skills of using Matlab;
ⅱ.You need to review Matlab programming language and M-file format.
ⅲ. You should have studied image segmentation and mathematical morphology methods.
Ⅲ.Experiment Contents
ⅰ.Read “bac.bmp” file (to do this by imread function), convert the color image into grayscale image, and then perform thresholding by auto threshoding method using “while loop” and display the results in a Matlab window.
程序：
%Iterative thresholdi
clear all;
im=imread('bac.bmp');
subplot(1,2,1);
imshow(im);
title('Gray image');
[Y X]=size(im);
S=sum(sum(im));
S=S/(X*Y);
D=0.1;
T=0;
im_bi=im>S;
while(abs(S-T)>D)
im1=double(im_bi).*double(im);
im2=double(abs(1-im_bi)).*double(im);
S1=sum(sum(im1))/sum(sum(im_bi));
S2=sum(sum(im2))/sum(sum(abs(1-im_bi)));
T=S;
S=(S1+S2)/2;
im_bi=im>S;
end
subplot(1,2,2);
imshow( im_bi);
title('image after Auto_thresholding');
ⅱ.Read “bw_bac.bmp” file and “bw_bac2.bmp”(to do this by imread function), perform mathematical morphology to fill the small holes in objects and display the results in a Matlab window.
腐蚀：
mask=[1 1 1;1 1 1;1 1 1];
im=imread('bw_bac.bmp');
figure(1)
subplot(1,2,1);
imagesc(im);
colormap(gray);
[Y,X]=size(im);
im_new=zeros(Y,X);
T=sum(sum(mask));
for kk=2:Y-1
for k=2:X-1
%Calculating sigma
imblock=im(k-1:k+1,kk-1:kk+1);
sigma=sum(sum(imblock&mask));
if sigma <T;
im_new(k,kk)=0;
else
im_new(k,kk)=im(k,kk);
end
end
end
subplot(1,2,2)
imagesc(im_new);
colormap(gray);
膨胀：
clear;
im=imread('bw_bac2.bmp');
figure(1)
subplot(1,2,1);
imagesc(im);
colormap(gray);
[Y,X]=size(im);
im_new=zeros(Y,X);
N=5;
mask=ones(N,N);
for i=(N+1)/2:Y-(N-1)/2
for j=(N+1)/2:X-(N-1)/2
%Calculating sigma
imblock=im(i-(N-1)/2:i+(N-1)/2,j-(N-1)/2:j+(N-1)/2);
sigma=sum(sum(imblock&mask));
if sigma >0
im_new(i,j)=1;
else
im_new(i,j)=im(i,j);
end
end
end
subplot(1,2,2)
imagesc(im_new);
colormap(gray);
iii.Read “Plate.jpg” file, convert the color image into gray scale image, then perform thresholding & mathematical morphology operation, display the results in Matlab window.
程序：
clear;
I=imread('Plate.JPG');
im=rgb2gray(I);
subplot(3,2,1);imshow(im);
title('Gray image');
[Y X]=size(im);
S=sum(sum(im));
S=S/(X*Y);
D=0.1;
T=0;
im_bi=im>S;
while(abs(S-T)>D)
im1=double(im_bi).*double(im);
im2=double(abs(1-im_bi)).*double(im);
S1=sum(sum(im1))/sum(sum(im_bi));
S2=sum(sum(im2))/sum(sum(abs(1-im_bi)));
T=S;
S=(S1+S2)/2;
im_bi=im>S;
end
subplot(3,2,2);
imshow( im_bi);
title('image after Auto_thresholding');
mask=[1 1 1;1 1 1;1 1 1];
im_new=zeros(Y,X);
T=sum(sum(mask));
for kk=2:X-1
for k=2:Y-1
imblock=im_bi(k-1:k+1,kk-1:kk+1);
sigma=sum(sum(imblock&mask));
if sigma <T;
new(k,kk)=0;
else
new(k,kk)=im_bi(k,kk);
end
end
end
subplot(3,2,3);
imshow( new);
title('image after Erosion ');
[A,B]=size(new);
N=3;
mask=ones(N,N);
for i=(N+1)/2:A-(N-1)/2
for j=(N+1)/2:B-(N-1)/2
block=new(i-(N-1)/2:i+(N-1)/2,j-(N-1)/2:j+(N-1)/2);
gma=sum(sum(block&mask));
if gma >0
im_new(i,j)=1;
else
im_new(i,j)=new(i,j);
end
end
end
subplot(3,2,4) imagesc(im_new); colormap(gray);
title('image after open');。