實(shí)用標(biāo)準(zhǔn)文案實(shí)用標(biāo)準(zhǔn)文案精彩文檔精彩文檔懵兇孝度PUTIANUNIVERSITY信息工程學(xué)院實(shí)驗(yàn)報(bào)告課程名稱：數(shù)字圖像處理 j人，一E …L -人…一 成績：實(shí)驗(yàn)項(xiàng)目名稱：實(shí)驗(yàn)四 圖像增強(qiáng) 實(shí)驗(yàn)時(shí)間：2016.11.08班級(jí)： 姓名：學(xué)號(hào)： 指導(dǎo)老師(簽名):一、實(shí)驗(yàn)?zāi)康?.了解圖像增強(qiáng)的目的及意義，加深對(duì)圖像增強(qiáng)的感性認(rèn)識(shí)，鞏固所學(xué)理論知識(shí)2.掌握?qǐng)D像空域增強(qiáng)算法的基本原理。.掌握?qǐng)D像空域增強(qiáng)的實(shí)際應(yīng)用及 MATLAB實(shí)現(xiàn)。.掌握頻域?yàn)V波的概念及方法。.熟練掌握頻域空間的各類濾波器。.掌握怎樣利用傅立葉變換進(jìn)行頻域?yàn)V波。.掌握?qǐng)D像頻域增強(qiáng)增強(qiáng)的實(shí)際應(yīng)用及 MATLAB實(shí)現(xiàn)。二、實(shí)驗(yàn)步驟及結(jié)果分析.基于幕次變換的圖像增強(qiáng)程序代碼：TOC\o"1-5"\h\zclear all;close all;I{1}=double(imread('fig534b.tif' ));I{1}=I{1}/255;figure,subplot(2,4,1);imshow(I{1},[]);hold onI{2}=double(imread('room.tif'));I{2}=I{2}/255;subplot(2,4,5);imshow(I{2},[]);hold onform=1:2Index=0;forlemta=[0.55]Index=Index+1;F{m}{Index}=I{m}.Alemta;subplot(2,4,(m-1)*4+Index+1),imshow(F{m}{Index},口)endend執(zhí)行結(jié)果：圖1哥次變換增強(qiáng)結(jié)果黑色區(qū)域被擴(kuò)展，變的清晰;當(dāng)r>1時(shí)，黑色區(qū)域被壓縮,黑色區(qū)域被擴(kuò)展，變的清晰;當(dāng)r>1時(shí)，黑色區(qū)域被壓縮,subplot(242);stem([0:N-1],Hist{1});title('規(guī)定化直方圖1');%倒三角形狀直方圖Hist{2}=abs(2*N-1-2*Index);Hist{2}=Hist{2}/sum(Hist{2});Hist_cumulation{2}=cumsum(Hist{2})；subplot(246);stem(0:N-1,Hist{2});title('規(guī)定化直方圖 2');%2.規(guī)定化處理Project{1}=zeros(N);Project{2}=zeros(N);Hist_result{1}=zeros(N);Hist_result{2}=zeros(N);form=1:2Image=I;%SML處理(SML,SingleMappingLaw射規(guī)則fork=1:NTemp=abs(Hist_image_cumulation(k)-Hist_cumulation{m});單映實(shí)驗(yàn)結(jié)果分析：由實(shí)驗(yàn)結(jié)果可知，當(dāng)r<1時(shí),變的幾乎不可見。.直方圖規(guī)定化處理程序代碼：clearallclccloseall%0.讀圖像I=double(imread('lena.tiff'));subplot(2,4,1);imshow(I,[]);title(‘原圖’)N=32;Hist_image=hist(I(:),N);Hist_image=Hist_image/sum(Hist_image)；Hist_image_cumulation=cumsum(Hist_image); %累計(jì)直方圖subplot(245);stem(0:N-1,Hist_image);title('原直方圖')；%1.設(shè)計(jì)目標(biāo)直方圖Index=0:N-1;%正態(tài)分布直方圖Hist{1}=exp(-(Index-N/2)A2/N);Hist{1}=Hist{1}/sum(Hist{1});Hist_cumulation{1}=cumsum(Hist{1})J

[Temp1,Project{m}(k)]=min(Temp);end%2.2變換后直方圖',num2str(m)]);%2.3',num2str(m)]);%2.3結(jié)果圖Step=256/N;forK=1:NTemp=find(Project{m}==k);ifisempty(Temp)Hist_result{m}(k)=0;elseHist_result{m}(k尸sum(Hist_image(TIndex=find(I>=Step*(k-1)&I<Step*k);Image(Index尸Project{m}(k);endemp));emp));endendsubplot(2,4,(m-1)*4+3);stem(0:N-1,Hist_result{m});title([′變換后的直方圖subplot(2,4,(m-1)*4+4),imshow(Image,[]);title([′變換后的結(jié)果圖',num2str(m)]);end執(zhí)行結(jié)果:原圖變換后的結(jié)果圖1變換后的結(jié)果圖2圖2直方圖規(guī)定化實(shí)驗(yàn)結(jié)果分析：由實(shí)驗(yàn)結(jié)果可知，采用直方圖規(guī)定化技術(shù)后，原圖的直方圖逼近規(guī)定化的直方圖，從而有相應(yīng)的變換后的結(jié)果圖1和變換后的結(jié)果圖2。%0.原圖I=double(imread('lena.tiff'));.灰度圖像常用平常、銳化濾波程序代碼：%0.原圖I=double(imread('lena.tiff'));clear all;close all;subplot(2,4,1);imshow(I,[]);title(‘原圖’)；%1.均值低通濾波H=fspecial('average',5);F{1}=double(filter2(H,I));subplot(2,4,2);imshow(F{1},[]);title('均值低通濾波’)；%2.gaussian 低通濾波H=fspecial('gaussian',7,3);F{2}=double(filter2(H,I));subplot(2,4,3);imshow(F{2},[]);title('高斯低通濾波’)；%3.增強(qiáng)圖像=原圖-均值低通濾波F{3}=2*I-F{1};subplot(2,4,4);imshow(uint8(F{3}),執(zhí)行結(jié)果：

[]);title('原圖-均值低通濾波‘);%4.增強(qiáng)圖像=原圖-高斯低通濾波F{4}=2*I-F{2};subplot(2,4,5);imshow(uint8(F{4}),[]);title('原圖-高斯低通濾波‘);%5.'prewitt' 邊緣算子增強(qiáng)H=fspecial('prewitt');F{5}=uint8(I+filter2(H,I));subplot(2,4,6);imshow(F{5},口);title('prewitt 邊緣算子增強(qiáng)’)；%6.'soble' 邊緣算子增強(qiáng)H=fspecial('sobel');F{6}=uint8(I+filter2(H,I));subplot(2,4,7);imshow(F{6},口);title('sobel邊緣算子增強(qiáng)’)；原圖均值低通濾波高斯低通濾波原圖-均值低通濾波原圖-高斯低通濾波prewitt邊緣算子增強(qiáng)sobel邊緣算子增強(qiáng)圖3灰色圖像平滑、銳化實(shí)驗(yàn)結(jié)果分析：由實(shí)驗(yàn)結(jié)果可知，均值和高斯濾波都使原圖模糊，而采用原圖減去低通濾波圖像方法、prewitt算子、sobel算子都可以增強(qiáng)圖像邊緣。4.頻率域?yàn)V波：對(duì)于給定圖像+噪聲，使用不同的頻域?yàn)V波器對(duì)圖像進(jìn)行濾波處理。(1)用Butterworth低通濾波器實(shí)現(xiàn)圖像信號(hào)的濾波運(yùn)算。程序代碼：clearall; I=imread('electric.tif' );closeall; subplot(2,3,1),imshow(I);title( '原%(a)讀入并顯示圖像electric.tif； 圖像’)；%(b)利用imnoise 命令在圖electric.tif上加入高斯(gaussian)噪聲；J=imnoise(I,'gaussian',0,0.01);subplot(2,3,2),imshow(J);title( '力口入高斯噪聲的圖像‘)；%(c)用Butterworth 低通濾波器實(shí)現(xiàn)圖像信號(hào)的濾波運(yùn)算，變換不同的截止頻率 dI1=fftshift(fft2(J));[m,n]=size(I1);N=2;d1=30;d2=50;d3=70;d4=90;n1=floor(m/2);n2=floor(n/2);fori=1:mforj=1:nd=sqrt((i-n1)A2+(j-n2)A2);H1=1/(1+(d/d1F(2*N));H2=1/(1+(d/d2)A(2*N));H3=1/(1+(d/d3)A(2*N));H4=1/(1+(d/d4)A(2*N));I3(i,j)=H1*I1(i,j);I5(i,j)=H2*I1(i,j);I7(i,j)=H3*I1(i,j);I9(i,j)=H4*I1(i,j);endendI3=ifftshift(I3);I4=real(ifft2(I3));I5=ifftshift(I5);I6=real(ifft2(I5));I7=ifftshift(I7);I8=real(ifft2(I7));I9=ifftshift(I9);I10=real(ifft2(I9));subplot(2,3,3),imshow(I4,[]),title('Butterworth低通濾波器d1=30');subplot(2,3,4),imshow(I6,[]),title('Butterworth 低通濾波器d2=50');subplot(2,3,5),imshow(I8,[]),title('Butterworth 低通濾波器d3=70');subplot(2,3,6),imshow(I10,[]),title('Butterworth 低通濾波器d4=90');加入高斯噪聲的圖像Butterworth低通濾波器d1=30加入高斯噪聲的圖像Butterworth低通濾波器d1=30執(zhí)行結(jié)果:原圖像JHIU,■.J?箭、■鼻.■■■■,iiK Butterworth低通濾波器d3=70Butterworth低通濾波器d4=90Butterworth低通濾波器d2=50HUM棚■???11V叫！M棚-V圖4Butterworth低通濾波器濾波結(jié)果實(shí)用標(biāo)準(zhǔn)文案實(shí)用標(biāo)準(zhǔn)文案sqrt((u-n1)A2+(v-n2)A2)<=d3H3(u,v)=1;sqrt((u-n1)A2+(v-n2)A2)<=d3H3(u,v)=1;elseH3(u,v)=0;endendendforu=1:mforv=1:nifsqrt((u-n1)A2+(v-n2)A2)<=d4H4(u,v)=1;elseH4(u,v)=0;endendendJ1=I1.*H1;J2=I1.*H2;J3=I1.*H3;J4=I1.*H4;K1=ifft2(ifftshift(J1));K2=ifft2(ifftshift(J2));K3=ifft2(ifftshift(J3));K4=ifft2(ifftshift(J4));C1=real(K1);C2=real(K2);C3=real(K3);C4=real(K4);subplot(2,3,3);imshow(C1,[]);title(‘濾波結(jié)果圖像，d1=30');subplot(2,3,4);imshow(C2,[]);title(‘濾波結(jié)果圖像，d2=50');subplot(2,3,5);imshow(C3,[]);title(‘濾波結(jié)果圖像，d3=70');subplot(2,3,6);imshow(C4,[]);title(‘濾波結(jié)果圖像，d4=90');實(shí)驗(yàn)結(jié)果分析：由實(shí)驗(yàn)結(jié)果可知，采用Butterworth低通濾波器對(duì)加噪聲的圖像進(jìn)行濾波運(yùn)算，濾波器的截止頻率d越小，濾波后的圖像越模糊。(2)用理想低通濾波器實(shí)現(xiàn)圖像信號(hào)的濾波運(yùn)算程序代碼：TOC\o"1-5"\h\zclear all;close all;I=imread('electric.tif' );subplot(2,3,1),imshow(I);title(圖像‘)；F=imnoise(I,'gaussian',0,0.01);subplot(2,3,2),imshow(F);title(入高斯噪聲的圖像‘)；%尊里葉變換并把頻譜中心移到中點(diǎn)F1=fft2(F);I1=fftshift(F1);%構(gòu)建理想低通濾波器[m,n]=size(I1);d1=30;d2=50;d3=70;d4=90;n1=floor(n/2);n2=floor(m/2);foru=1:mforv=1:nifsqrt((u-n1)A2+(v-n2)A2)<=d1H1(u,v)=1;elseH1(u,v)=0;endendendforu=1:mforv=1:nifsqrt((u-n1)A2+(v-n2)A2)<=d2H2(u,v)=1;elseH2(u,v)=0;endendendforu=1:mforv=1:nif執(zhí)行結(jié)果:精彩文檔實(shí)用標(biāo)準(zhǔn)文案實(shí)用標(biāo)準(zhǔn)文案精彩文檔精彩文檔原圖像加入高斯噪聲的圖像濾波結(jié)果圖像，d1=30濾波結(jié)果圖像,d2=50濾波結(jié)果圖像，d3=70濾波結(jié)果圖像，d4=90出H1=1/(1+(d1/d)A(2*N));H2=1/(1+(d2/d)A(2*N));I3(i,j)=H1*I1(i,j);原圖像加入高斯噪聲的圖像濾波結(jié)果圖像，d1=30濾波結(jié)果圖像,d2=50濾波結(jié)果圖像，d3=70濾波結(jié)果圖像，d4=90出H1=1/(1+(d1/d)A(2*N));H2=1/(1+(d2/d)A(2*N));I3(i,j)=H1*I1(i,j);I5(i,j)=H2*I1(i,j);原 endend圖 I3=ifftshift(I3);I4=real(ifft2(I3));I5=ifftshift(I5);I6=real(ifft2(I5));subplot(1,3,2),imshow(I4,[]),title('Butterworth 高通濾波器d1=30');subplot(1,3,3),imshow(I6,[]),title('Butterworth 高通濾波器d2=50');圖5理想低通濾波器濾波結(jié)果實(shí)驗(yàn)結(jié)果分析：由實(shí)驗(yàn)結(jié)果可知，采用理想低通濾波器對(duì)加噪聲的圖像進(jìn)行濾波運(yùn)算，濾波器的濾波半徑d越小，濾波后的圖像越模糊，且出現(xiàn)明顯的振鈴現(xiàn)象，相比于巴特沃斯低通濾波器，理想低通濾波器的濾波效果會(huì)比較差。(3)采用巴特沃斯高通濾波器對(duì)room.tif圖像進(jìn)行銳化濾波，并顯示濾波結(jié)果圖像。程序代碼：clear all;close all;%(d)讀入并顯示原始圖像 room.tif;I=imread('room.tif');subplot(1,3,1),imshow(I);title(圖像room');%(e)采用巴特沃斯高通濾波器對(duì) room.tif像進(jìn)行銳化濾波，變換不同的濾波半徑I1=fftshift(fft2(I));[m,n]=size(I1);N=2;d1=10;d2=50;n1=floor(m/2);n2=floor(n/2);fori=1:mforj=1:nd=sqrt((i-n1)A2+(j-n2)A2);執(zhí)行結(jié)果：原圖像roomButterworth原圖像roomButterworth高通濾波器d1=30Butterworth高通濾波器d2=50圖6巴特沃斯高通濾波器銳化濾波結(jié)果實(shí)驗(yàn)結(jié)果分析：由實(shí)驗(yàn)結(jié)果可知，采用Butterworth高通濾波器對(duì)圖像進(jìn)行濾波運(yùn)算，濾波后圖像的邊緣和細(xì)節(jié)變的更加突出，是一種對(duì)圖像的銳化處理。三、實(shí)驗(yàn)中遇到問題及解決方法實(shí)驗(yàn)中遇到的問題有：初期對(duì)圖像在頻域空間的濾波不太了解，不懂得如何利用傅立葉變換進(jìn)行頻域?yàn)V波；解決的方法：通過參考課本中例題及參考程序，逐步分析，加深理解。四、實(shí)驗(yàn)心得體會(huì)通過此次試驗(yàn)，初步掌握?qǐng)D像空域增強(qiáng)算法的基本原理并能在實(shí)際應(yīng)用及 MATLAB中實(shí)現(xiàn)；通過熟悉各類濾波器對(duì)圖像處理的應(yīng)用；加深對(duì)圖像增強(qiáng)的感性認(rèn)識(shí)，鞏固所學(xué)理論知識(shí)。五、源程序清單%%%1.基于募次變換的圖像增強(qiáng)TOC\o"1-5"\h\zclear all;close all;I{1}=double(imread('fig534b.tif' ));I{1}=I{1}/255;figure,subplot(2,4,1);imshow(I{1},[]);hold onI{2}=double(imread('room.tif'));I{2}=I{2}/255;subplot(2,4,5);imshow(I{2},[]);hold onform=1:2Index=0;forlemta=[0.55]Index=Index+1;F{m}{Index}=I{m}.Alemta;subplot(2,4,(m-1)*4+Index+1),imshow(F{m}{Index},口)endend實(shí)用標(biāo)準(zhǔn)文案實(shí)用標(biāo)準(zhǔn)文案%%%2.直方圖規(guī)定化處理clearallclccloseall%0.讀圖像I=double(imread('lena.tiff'));subplot(2,4,1);imshow(I,[]);title(‘原圖’)N=32;Hist_image=hist(I(:),N);Hist_image=Hist_image/sum(Hist_image);Hist_image_cumulation=cumsum(Hist_image); 濯計(jì)直方圖subplot(245);stem(0:N-1,Hist_image);title('原直方圖')；%1.設(shè)計(jì)目標(biāo)直方圖Index=0:N-1;%正態(tài)分布直方圖Hist{1}=exp(-(Index-N/2)A2/N);Hist{1}=Hist{1}/sum(Hist{1});Hist_cumulation{1}=cumsum(Hist{1});subplot(242);stem([0:N-1],Hist{1});title('規(guī)定化直方圖1');%倒三角形狀直方圖Hist{2}=abs(2*N-1-2*Index);Hist{2}=Hist{2}/sum(Hist{2});Hist_cumulation{2}=cumsum(Hist{2});subplot(246);stem(0:N-1,Hist{2});title('規(guī)定化直方圖2');%2.規(guī)定化處理Project{1}=zeros(N);Project{2}=zeros(N);Hist_result{1}=zeros(N);Hist_result{2}=zeros(N);form=1:2Image=I;%SML處理(SML,SingleMappingLaw 單映射規(guī)則fork=1:NTemp=abs(Hist_image_cumulation(k)-Hist_cumulation{m});[Temp1,Project{m}(k)]=min(Temp);end%2.2變換后直方圖精彩文檔fork=1:NTemp=find(Project{m}==k);ifisempty(Temp)Hist_result{m}(k)=0;elseHist_result{m}(k尸sum(Hist_image(Temp));endendsubplot(2,4,(m-1)*4+3);stem(0:N-1,Hist_result{m});title(['變換后的直方圖‘，num2str(m)]);%2.3結(jié)果圖Step=256/N;forK=1:NIndex=find(I>=Step*(k-1)&I<Step*k);Image(Index尸Project{m}(k);endsubplot(2,4,(m-1)*4+4),imshow(Image,[]);title(['變換后的結(jié)果圖‘，num2str(m)]);end%%%3.灰度圖像常用平常、銳化濾波clear all;close all;%0.原圖I=double(imread('lena.tiff'));subplot(2,4,1);imshow(I,[]);title( '原圖')；%1.均值低通濾波H=fspecial('average',5);F{1}=double(filter2(H,I));subplot(2,4,2);imshow(F{1},[]);title( '均值低通濾波%2.gaussian低通濾波H=fspecial( 'gaussian' ,7,3);F{2}=double(filter2(H,I));subplot(2,4,3);imshow(F{2},[]);title( '高斯低通濾波%3.增強(qiáng)圖像=原圖-均值低通濾波F{3}=2*I-F{1};subplot(2,4,4);imshow(uint8(F{3}),[]);title( '原圖%4.增強(qiáng)圖像=原圖-高斯低通濾波F{4}=2*I-F{2};subplot(2,4,5);imshow(uint8(F{4}),口);title( '原圖%5.'prewitt' 邊緣算子增強(qiáng)H=fspecial('prewitt');F{5}=uint8(I+filter2(H,I));精彩文檔););均值低通濾波?);高斯低通濾波‘);subplot(2,4,6);imshow(F{5},[]);title( 'prewitt 邊緣算子增強(qiáng)')；%6.'soble' 邊緣算子增強(qiáng)H=fspecial('sobel');F{6}=uint8(I+filter2(H,I));subplot(2,4,7);imshow(F{6},[]);title( 'sobel 邊緣算子增強(qiáng)');%%%4.(1)Butterworth 低通濾波器實(shí)現(xiàn)圖像信號(hào)的濾波運(yùn)算TOC\o"1-5"\h\zclear all ;close all ;%(a) 讀入并顯示圖像 electric.tif；I=imread('electric.tif' );subplot(2,3,1),imshow(I);title( '原圖像');%(b)利用imnoise 命令在圖像electric.tif 上加入高斯(gaussian)噪聲;J=imnoise(I,'gaussian',0,0.01);subplot(2,3,2),imshow(J);title( '加入高斯噪聲的圖像');%(c)用Butterworth 低通濾波器實(shí)現(xiàn)圖像彳t號(hào)的濾波運(yùn)算 ，變換不同的截止頻率d:d1=30;d2=50;d3=70;d4=90I1=fftshift(fft2(J));[m,n]=size(I1);N=2;d1=30;d2=50;d3=70;d4=90;n1=floor(m/2);n2=floor(n/2);fori=1:mforj=1:nd=sqrt((i-n1)A2+(j-n2)A2);H1=1/(1+(d/d1F(2*N));H2=1/(1+(d/d2)A(2*N));H3=1/(1+(d/d3)A(2*N));H4=1/(1+(d/d4)A(2*N));I3(i,j)=H1*I1(i,j);I5(i,j)=H2*I1(i,j);I7(i,j)=H3*I1(i,j);I9(i,j)=H4*I1(i,j);endendI3=ifftshift(I3);I4=real(ifft2(I3));I5=ifftshift(I5);I6=real(ifft2(I5));I7=ifftshift(I7);I8=real(ifft2(I7));I9=ifftshift(I9);I10=real(ifft2(I9));subplot(2,3,3),imshow(I4,[]),title('Butterworth低通濾波器d1=30'subplot(2,3,4),imshow(I6,[]),title('Butterworth低通濾波器d2=50'subplot(2,3,5),imshow(I8,[]),title('Butterworth低通濾波器d3=70'精彩文檔subplot(2,3,6),imshow(I10,[]),title( 'Butterworth 低通濾波器d4=90');%%%4.(2)用理想低通濾波器實(shí)現(xiàn)圖像信號(hào)的濾波運(yùn)算TOC\o"1-5"\h\zclear all;close all;I=imread('electric.tif' );subplot(2,3,1),imshow(I);title( '原圖像')；F=imnoise(I,'gaussian',0,0.01);subplot(2,3,2),imshow(F);title( '加入高斯噪聲的圖像’)；%傅里葉變換并把頻譜中心移到中點(diǎn)F1=fft2(F);I1=fftshift(F1);%勾建理想低通濾波器[m,n]=size(I1);d1=30;d2=50;d3=70;d4=90;n1=floor(n/2);n2=floor(m/2);foru=1:mforv=1:nifsqrt((u-n1)A2+(v-n2)A2)<=d1H1(u,v)=1;elseH1(u,v)=0;endendendforu=1:mforv=1:nifsqrt((u-n1)A2+(v-n2)A2)<=d2H2(u,v)=1;elseH2(u,v)=0;endendendforu=1:mforv=1:nifsqrt((u-n1)A2+(v-n2)A2)<=d3H3(u,v)=1;elseH3(u,v)=0;endendendforu=1:mforv=1:n精彩文檔實(shí)用標(biāo)準(zhǔn)文案實(shí)用標(biāo)準(zhǔn)文案精彩文檔精彩文檔ifsqrt((u-n1)A2+(v-n2)A2)<=d4H4(u,v)=1;elseH4(u,v)=0;endendendJ1=I1.*H1;J2=I1.*H2;J3=I1.*H3;J4=I1.*H4;K1=ifft2(ifftshift(J1));K2=ifft2(ifftshift(J2));K3=ifft2(ifftshift(J3));K4=ifft2(ifftshift(J4));C1=real(K1);C2=real(K2);C3=real(K3);濾波結(jié)果圖像,d1=30'）；濾波結(jié)果圖像,d2=50'）；濾波結(jié)果圖像,d3=70'）；濾波結(jié)果圖像,d4=90'）；低通濾波器對(duì)加噪圖像進(jìn)行濾波對(duì)比原圖像低通濾波器對(duì)加噪圖像進(jìn)行濾波對(duì)比原圖像‘）；加入高斯噪聲的圖像‘）；subplot(2,3,3);imshow(C1,[]);title(subplot(2,3,4);imshow(C2,[]);title(subplot(2,3,5);imshow(C3,[]);title(subplot(2,3,6);imshow(C4,[]);title(%%%4(