Conv2用法

根据帮助

C = conv2(A,B) computes the two-dimensional convolution of matrices A and B. If one of these matrices describes a two-dimensional finite impulse response (FIR) filter, the other matrix is filtered in two dimensions

在敲姚敏的数字图像处理过程中，平滑

I=imread('lena.jpg');
J=imnoise(I,'salt & pepper',0.02);

subplot(231),imshow(I);title('chart1');
subplot(232),imshow(J);title('chart1+noise');

[M,N,P]=size(J);
if(P==3)
    I=rgb2gray(J);
    I=double(I);
    end

k1=filter2(fspecial('average', 3), double(I));
k2=filter2(fspecial('average',7),double(I));
k3=filter2(fspecial('average',9),double(I));

k4=filter2(fspecial('average',5),double(I));

subplot(233),imshow(uint8(k1));title('3');
subplot(234),imshow(uint8(k2));title('4');
subplot(235),imshow(uint8(k3));title('5');
subplot(236),imshow(uint8(k4));title('6');

 

发现我敲的lena.jpg是24位的，所以如果直接写

k1=filter2(fspecial('average', 3), J);

会出错，需要添加上面的红色部分。