數(shù)字圖像處理第二次作業(yè)

1、1.此處可以補(bǔ)充上一次未完成的作業(yè)；2.將一幅圖像分別進(jìn)行直方圖均衡化和規(guī)定化操作；s = imread('a1.jpg');I=rgb2gray(s); figure imshow(I) figure imhist(I); II = histeq(I); figure imhist(II); figure imshow(II) s = imread('a1.jpg');I=rgb2gray(s);m,n = size(I);for i=1 :8:257 count(i)=i;endN = histeq(I,count); figure imshow(N) fi

2、gure imhist(N); 3.將一幅被椒鹽噪聲影響的圖像分別使用3×3、5×5和7×7的模版進(jìn)行均值濾波，將原圖像和濾波之后的圖像顯示出來。并總結(jié)說明模版尺寸對(duì)圖像效果的影響；i = imread('c1.png');i=rgb2gray(i); j=imnoise(i,'salt & pepper',0.02);subplot(231), imshow(i);title('ԭͼ')subplot(232), imshow(j);title('

3、4;í¼ÓÁ˽·ÑÎÔëÉù');K1 = filter2(fspecial('average',3),j);K2 = filter2(fspecial('average',5),j);K3 = filter2(fspecial('average',7),j);subplot(233), imshow(uint8(K1);title('3X3ƽ»¬Â

4、˲¨')subplot(234), imshow(uint8(K2);title('5X5ƽ»¬Â˲¨')subplot(235), imshow(uint8(K3);title('7X7ƽ»¬Â˲¨') 當(dāng)所用平板模板尺寸增大時(shí)，對(duì)噪聲的消除有所增強(qiáng)，但同時(shí)所得到的圖像便得更加模糊，細(xì)節(jié)的銳化部分逐步減弱。4.將一幅被椒鹽噪聲影響的圖像分別使用3×

5、;3和5×5的均值濾波和中值濾波恢復(fù)，并總結(jié)說明均值濾波與中值濾波方法對(duì)圖像效果的影響；i = imread('c1.png');i=rgb2gray(s); j=imnoise(i,'salt & pepper',0.02);subplot(231), imshow(i);title('ԭͼ')subplot(232), imshow(j);title('Ìí¼ÓÁ˽·ÑÎ&

6、#212;ëÉù');K1 = filter2(fspecial('average',3),j);K2 = filter2(fspecial('average',5),j);subplot(233), imshow(uint8(K1);title('3X3ƽ»¬Â˲¨')subplot(234), imshow(uint8(K2);title('5X5ƽ»¬Â

7、3;²¨') K3 = medfilt2(j,3 3);K4 = medfilt2(j,5 5);subplot(235), imshow(K3);title('3X3ÖÐÖµÂ˲¨')subplot(236), imshow(K4);title('5X5ÖÐÖµÂ˲¨') 平均值濾波減少了圖像的尖銳變化，但會(huì)使圖像變得模糊，中值濾波克服這一現(xiàn)象，他在衰減噪聲的同時(shí)保持了圖

8、像細(xì)節(jié)的清晰。5.處理運(yùn)動(dòng)造成的圖像模糊，要求：（1）將一幅圖像進(jìn)行運(yùn)動(dòng)模糊（水平位移50pix，運(yùn)動(dòng)角度60度）；（2）將該模糊圖像進(jìn)行非精確復(fù)原；（3）將該模糊圖像進(jìn)行精確復(fù)原。i = imread('c1.png');i=rgb2gray(s);l=50;t=60; psf = fspecial('motion',l,t);m = imfilter(i,psf,'circular','conv'); subplot(121), imshow(i);title('ԭͼ'

9、;)subplot(122), imshow(m);title('Ä£ºý'); imwrite(m,'a4.jpg'); i,j = imread('a4.jpg'); l=50;t=60; psf = fspecial('motion',l,t);m,n = deconvblind(i,psf,30);figure; imshow(m);figure; imshow(n,'notruesize'); i,j = imread('a4.jpg'); l=30

10、;t=30; psf = fspecial('motion',l,t);m,n = deconvblind(i,psf,30);figure; imshow(m);figure; imshow(n,'notruesize'); 6.P102，例5.3，逆濾波與維納濾波的比較程序（修改參數(shù)），并給出逆濾波與維納濾波在處理運(yùn)動(dòng)模糊時(shí)的優(yōu)劣；F=checkerboard(8); figure(1); imshow(F,); PSF=fspecial('motion',8,50); MF=imfilter(F,PSF,'circular'

11、); noise=imnoise(zeros(size(F),'gaussian',0,0.001); MFN=MF+noise; figure(2); imshow(MFN,); NSR=sum(noise(:).2)/sum(MFN(:).2); figure(3); imshow(deconvwnr(MFN,PSF),); figure(4); imshow(deconvwnr(MFN,PSF,NSR),); 維納濾波在圖像受噪聲影響時(shí)效果比逆濾波好，而且噪聲越強(qiáng)優(yōu)勢(shì)越明顯。7.分別使用梯度算子、拉普拉斯算子、soble水平和垂直算子對(duì)圖像進(jìn)行銳化處理，并就區(qū)別進(jìn)行分析說

12、明；Prewitt:A=imread(' c1.png '); B=rgb2gray(A);subplot(131),imshow(B);H=fspecial('prewitt');TH=filter2(H,B);subplot(132),imshow(TH,);H=H'TH=filter2(H,B);subplot(133),imshow(TH,);拉普拉斯算子：A=imread('a1.jpg'); B=rgb2gray(A);h=1 1 1;1 -8 1;1 1 1I2=filter2(h,B);subplot(121),imsho

13、w(B,);subplot(122),imshow(I2,);拉普拉斯算子比較適用于改善因光線的漫反射而造成的圖像模糊Soble水平和垂直： A=imread('a1.jpg'); B=rgb2gray(A); subplot(131),imshow(B);H=fspecial('sobel');TH=filter2(H,B);subplot(132),imshow(TH,);H=H'TH=filter2(H,B);subplot(133),imshow(TH,); 8.使用低通濾波選擇不同的截止頻率處理此圖像。（截止頻率為15/45/65）figure

14、(1);RGB=imread('a1.jpg');J=rgb2gray(RGB);subplot(221),imshow(J);J=double(J); f=fft2(J); g=fftshift(f); M,N=size(f); n1=floor(M/2); n2=floor(N/2); d0=15; for i=1:M for j=1:N d=sqrt(i-n1)2+(j-n2)2); if d<=d0; h=1; else h=0; end g(i,j)=h*g(i,j); end end g=ifftshift(g); g=uint8(real(ifft2(g); subplot(222); imshow(g); g=fftshift(f); d0=45; for i=1:M for j=1:N d=sqrt(i-n1)2+(j-n2)2); if d<=d0; h=1; else h=0; end g(i,j)=h*g(i,j); end end g=ifftshift(g); g=uint8