用Sobel算子、Roberts算子、Prewitt算子对图像进行边缘检测的程序，在matlab环境下，程序要完整，最好有图 分别利用 Roberts、Prewitt、Sobel 和 L...
Matlab\u5173\u4e8e\u56fe\u50cf\u8fb9\u7f18\u63d0\u53d6\uff0c\u7528Sobel\u7b97\u5b50\u3001Roberts\u7b97\u5b50\u3001Prewitt\u7b97\u5b50\uff0c\u52a0QQ\u8be6\u8c08 \u6025\u7528\uff01\uff014.2.1 Roberts\u7b97\u6cd5\u539f\u7406
Roberts\u7b97\u5b50\u662f\u4e00\u79cd\u6700\u7b80\u5355\u7684\u7b97\u5b50\uff0c\u662f\u4e00\u79cd\u5229\u7528\u5c40\u90e8\u5dee\u5206\u7b97\u5b50\u5bfb\u627e\u8fb9\u7f18\u7684\u7b97\u5b50\uff0c\u4ed6\u91c7\u7528\u5bf9\u89d2\u7ebf\u65b9\u5411\u76f8\u90bb\u4e24\u8c61\u7d20\u4e4b\u5dee\u8fd1\u4f3c\u68af\u5ea6\u5e45\u503c\u68c0\u6d4b\u8fb9\u7f18\u3002\u68c0\u6d4b\u5782\u76f4\u8fb9\u7f18\u7684\u6548\u679c\u597d\u4e8e\u659c\u5411\u8fb9\u7f18\uff0c\u5b9a\u4f4d\u7cbe\u5ea6\u9ad8\uff0c\u5bf9\u566a\u58f0\u654f\u611f,\u65e0\u6cd5\u6291\u5236\u566a\u58f0\u7684\u5f71\u54cd\u3002
4.2.2 \u7b97\u6cd5\u6d41\u7a0b
Roberts\u7b97\u5b50\u57282\u00d72\u9886\u57df\u4e0a\u8ba1\u7b97\u5bf9\u89d2\u5bfc\u6570
\uff084-1\uff09
\u6210\u4e3aRoberts\u4ea4\u53c9\u7b97\u5b50\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u4e3a\u4e86\u7b80\u5316\u8ba1\u7b97\uff0c\u7528\u68af\u5ea6\u51fd\u6570\u7684Roberts\u7edd\u5bf9\u503c\u6765\u8fd1\u4f3c
\uff084-2\uff09\u53e6\u5916\u8fd8\u53ef\u4ee5\u7528Roberts \u6700\u5927\u7b97\u5b50\u6765\u8ba1\u7b97
\uff084-3\uff09
\u4e0a\u5f0f\u80fd\u591f\u63d0\u4f9b\u8f83\u597d\u7684\u4e0d\u53d8\u6027\u8fb9\u7f18\u53d6\u5411\u3002\u5bf9\u4e8e\u540c\u7b49\u957f\u5ea6\u4f46\u53d6\u5411\u4e0d\u540c\u7684\u8fb9\u7f18\uff0c\u5e94\u7528Roberts\u6700\u5927\u503c\u7b97\u5b50\u6bd4\u5e94\u7528Roberts\u4ea4\u53c9\u7b97\u5b50\u6240\u5f97\u5230\u7684\u5408\u6210\u5e45\u5ea6\u53d8\u5316\u5c0f\u3002Roberts\u8fb9\u7f18\u68c0\u6d4b\u7b97\u5b50\u7684\u5377\u79ef\u7b97\u5b50\u4e3a
Roberts \u8fb9\u7f18\u7b97\u5b50\u65b9\u5411\u6a21\u7248
\u7531\u4e0a\u9762\u4e24\u4e2a\u5377\u79ef\u7b97\u5b50\u5bf9\u56fe\u50cf\u8fd0\u7b97\u540e\uff0c\u4ee3\u5165\uff083-7\uff09\u5f0f\uff0c\u53ef\u6c42\u5f97\u56fe\u50cf\u7684\u68af\u5ea6\u5e45\u5ea6\u503c\uff0c\u7136\u540e\u9009\u53d6\u95e8\u9650TH\uff0c\u505a\u5982\u4e0b\u5224\u65ad>TH\uff0c\u4e3a\u9636\u8dc3\u72b6\u8fb9\u7f18\u70b9\u4e3a\u4e00\u4e2a\u4e8c\u503c\u56fe\u50cf\uff0c\u4e5f\u5c31\u662f\u56fe\u50cf\u7684\u8fb9\u7f18\u56fe\u50cf\u30024.4.1 Prewitt \u7b97\u6cd5\u539f\u7406
Prewitt\u8fb9\u7f18\u7b97\u5b50\u662f\u4e00\u79cd\u8fb9\u7f18\u6837\u677f\u7b97\u5b50\u3002Prewitt \u4ece\u52a0\u5927\u8fb9\u7f18\u68c0\u6d4b\u7b97\u5b50\u7684\u6a21\u677f\u5927\u5c0f\u51fa\u53d1\uff0c\u75312\u00d72 \u6269\u5927\u52303\u00d73 \u6765\u8ba1\u7b97\u5dee\u5206\u7b97\u5b50\uff0c\u91c7\u7528Prewitt \u7b97\u5b50\u4e0d\u4ec5\u80fd\u68c0\u6d4b\u8fb9\u7f18\u70b9\uff0c\u800c\u4e14\u80fd\u6291\u5236\u566a\u58f0\u7684\u5f71\u54cd\u3002
Prewitt \u91c7\u7528\u8ba1\u7b97\u504f\u5fae\u5206\u4f30\u8ba1\u7684\u65b9\u6cd5\uff0c\u7531\u5f0f\uff084-9\uff09\u6240\u793a\u7684\u4e24\u4e2a\u5377\u79ef\u7b97\u5b50\u5f62\u6210\u4e86Prewitt\u8fb9\u7f18\u7b97\u5b50\uff0c\u6837\u677f\u7b97\u5b50\u7531\u7406\u60f3\u7684\u8fb9\u7f18\u5b50\u56fe\u50cf\u6784\u6210\uff0c\u4f9d\u6b21\u7528\u8fb9\u7f18\u6837\u677f\u53bb\u68c0\u6d4b\u56fe\u50cf\uff0c\u4e0e\u88ab\u68c0\u6d4b\u533a\u57df\u6700\u4e3a\u76f8\u4f3c\u7684\u6837\u677f\u7ed9\u51fa\u6700\u5927\u503c\uff0c\u7528\u8fd9\u4e2a\u6700\u5927\u503c\u4f5c\u4e3a\u7b97\u5b50\u7684\u8f93\u51fa
\uff084-9\uff09
\u53e6\u4e00\u79cd\u65b9\u6cd5\u662f\uff0c\u53ef\u4ee5\u5c06Prewitt\u7b97\u5b50\u6269\u5c55\u5230\u516b\u4e2a\u65b9\u5411\uff0c\u6bcf\u4e2a\u6a21\u7248\u5bf9\u7279\u5b9a\u7684\u8fb9\u7f18\u65b9\u5411\u505a\u51fa\u6700\u5927\u54cd\u5e94\uff0c\u6240\u67098\u4e2a\u65b9\u5411\u4e2d\u6700\u5927\u503c\u4f5c\u4e3a\u8fb9\u7f18\u5e45\u5ea6\u56fe\u50cf\u7684\u8f93\u51fa\uff0c\u8fd9\u4e9b\u7b97\u5b50\u6837\u677f\u7531\u79bb\u7ebf\u7684\u8fb9\u7f18\u5b50\u56fe\u50cf\u6784\u6210\u3002\u4f9d\u6b21\u7528\u8fb9\u7f18\u6837\u677f\u53bb\u68c0\u6d4b\u56fe\u50cf\uff0c\u4e0e\u88ab\u68c0\u6d4b\u533a\u57df\u6700\u4e3a\u76f8\u4f3c\u7684\u7684\u6837\u677f\u7ed9\u51fa\u6700\u5927\u503c\u3002\u5b9a\u4e49Prewitt \u8fb9\u7f18\u68c0\u6d4b\u7684\u7b97\u5b50\u6a21\u7248\u5982\u4e0b\uff1a
\uff081\uff091\u65b9\u5411 \uff082\uff092\u65b9\u5411 \uff083\uff093\u65b9\u5411 \uff084\uff094\u65b9
clear;
fid=fopen('d:\image\Lena.img','r'); %\u6253\u5f00\u65e0\u683c\u5f0f\u6587\u4ef6
data1=(fread(fid,[256,256],'uint8'))';
subplot(2,3,1),imagesc(data1);
colormap(gray);
title('LENA','Color','r');
subplot(2,3,2);
data2=uint8(data1);
R=edge(data2,'Roberts');
imagesc(R);
title('Roberts\u68c0\u6d4b\u7b97\u5b50');
subplot(2,3,3);
data2=uint8(data1);
Q=edge(data2,'Prewitt');
imagesc(Q);
title('Prewitt\u68c0\u6d4b\u7b97\u5b50');
subplot(2,3,4);
data2=uint8(data1);
S=edge(data2,'Sobel');
imagesc(S);
title('Sobel\u68c0\u6d4b\u7b97\u5b50');
subplot(2,3,5);
data2=uint8(data1);
T=edge(data2,'Log');
imagesc(T);
title('Log\u68c0\u6d4b\u7b97\u5b50');
Matlab\u4e2d\u8fd0\u884c\u8fc7\u7684 \u6b63\u786e\u7684\uff01
close all
clear all
I=imread('tig.jpg'); %读取图像
I1=im2double(I); %将彩图序列变成双精度
I2=rgb2gray(I1); %将彩色图变成灰色图
[thr, sorh, keepapp]=ddencmp('den','wv',I2);
I3=wdencmp('gbl',I2,'sym4',2,thr,sorh,keepapp); %小波除噪
I4=medfilt2(I3,[9 9]); %中值滤波
I5=imresize(I4,0.2,'bicubic'); %图像大小
BW1=edge(I5,'sobel'); %sobel图像边缘提取
BW2=edge(I5,'roberts'); %roberts图像边缘提取
BW3=edge(I5,'prewitt'); %prewitt图像边缘提取
BW4=edge(I5,'log'); %log图像边缘提取
BW5=edge(I5,'canny'); %canny图像边缘提取
h=fspecial('gaussian',5); %高斯滤波
BW6=edge(I5,'zerocross',[ ],h); %zerocross图像边缘提取
figure;
subplot(1,3,1); %图划分为一行三幅图，第一幅图
imshow(I2); %绘图
figure;
subplot(1,3,1);
imshow(BW1);
title('Sobel算子');
subplot(1,3,2);
imshow(BW2);
title('Roberts算子');
subplot(1,3,3);
imshow(BW3);
title('Prewitt算子');
绛旓細Sobel绠楀瓙鏄竴绉嶅熀浜庣鏁ｅ井鍒嗙殑杈圭紭妫娴嬬畻瀛愶紝瀹冪粨鍚堜簡楂樻柉骞虫粦鍜屽井鍒嗘眰瀵肩殑鎬濇兂銆係obel绠楀瓙閫氳繃璁＄畻鍥惧儚涓瘡涓儚绱犵偣鍛ㄥ洿閭诲煙鍐呭儚绱犵殑鐏板害鍔犳潈宸潵浼拌璇ョ偣鐨勬搴﹀箙搴﹀拰鏂瑰悜銆傜浉姣斾簬Roberts绠楀瓙锛孲obel绠楀瓙瀵瑰櫔澹板叿鏈変竴瀹氱殑鎶戝埗浣滅敤銆傚洜涓哄畠鍦ㄨ绠楁搴︽椂锛屼笉浠呰冭檻浜嗙浉閭诲儚绱犵殑宸硷紝杩樿冭檻浜嗚窛绂昏緝杩滅殑鍍忕礌瀵瑰綋...
绛旓細imshow(BW1); title('Sobel绠楀瓙'); subplot(1,3,2); imshow(BW2); title('Roberts绠楀瓙'); subplot(1,3,3); imshow(BW3); title('Prewitt绠楀瓙'); 鍚戝乏杞瑋鍚戝彸杞 鏈洖绛旂敱鐢佃剳缃戠粶鍒嗙被杈句汉 钁ｈ緣鎺ㄨ崘 51 2 宸茶禐杩 宸茶俯杩< 璇勮(7) 鍒嗕韩 寰俊鎵竴鎵 鏂版氮寰崥 QQ绌洪棿 涓炬姤 鏀惰捣 鍏朵粬...
绛旓細title('Sobel绠楀瓙');subplot(1,3,2);imshow(BW2);title('Roberts绠楀瓙');subplot(1,3,3);imshow(BW3);title('Prewitt绠楀瓙');
绛旓細Robert绠楀瓙鏄涓涓竟缂樻娴绠楀瓙锛鎻愬嚭鑰匧awrence Roberts in 1963.Sobel杈圭紭绠楀瓙锛屽綋骞翠綔鑰呭苟娌℃湁鍏紑鍙戣〃杩囪鏂囷紝浠呬粎鏄湪涓娆″崥澹敓璇鹃璁ㄨ浼(1968)涓婃彁鍑("A 3x3 Isotropic Gradient Operator for Image Processing")锛屽悗鍦1973骞村嚭鐗堢殑涓鏈笓钁楋紙"Pattern Classification and Scene Analysis"锛夌殑鑴氭敞閲...
绛旓細Roberts绠楀瓙鏄竴绉嶆渶绠鍗曠殑绠楀瓙锛鏄竴绉鍒╃敤灞閮ㄥ樊鍒嗙畻瀛愬鎵捐竟缂樼殑绠楀瓙锛屼粬閲囩敤瀵硅绾挎柟鍚戠浉閭讳袱璞＄礌涔嬪樊杩戜技姊害骞呭兼娴嬭竟缂樸傛娴嬪瀭鐩磋竟缂樼殑鏁堟灉濂戒簬鏂滃悜杈圭紭锛屽畾浣嶇簿搴﹂珮锛屽鍣０鏁忔劅,鏃犳硶鎶戝埗鍣０鐨勫奖鍝嶃4.2.2 绠楁硶娴佺▼ Roberts绠楀瓙鍦2脳2棰嗗煙涓婅绠楀瑙掑鏁 锛4-1锛夋垚涓篟oberts浜ゅ弶绠楀瓙銆傚湪瀹為檯...
绛旓細淇哄氨缁欎綘鍐欎釜sobel鐨勶紝浣犳妸sobel妯℃澘鎹㈡垚robert妯℃澘灏監K浜嗐傛湰鏉obel鎵鹃槇鍊艰繕鏈変釜灏忕畻娉曪紝涓嶈繃涓鑸笉瑕佹眰鐨勶紝淇哄氨鐢ㄩ粍閲戝垎鍓茬偣涔樹互255鏇夸唬浜嗐俿obel鍗风Н浠ｇ爜濡備笅锛歷oid CSobelDlg::CreateSobolImage(void){ static const int sizeOfSobelMask = 9;static int sobelMaskHor[sizeOfSobelMask] = { -1,...
绛旓細涓鑸浣跨敤涓闃跺井鍒嗗拰浜岄樁寰垎妫娴嬭竟缂橈紝鍦ㄨ竟缂樹綅缃紝涓闃跺井鍒嗙殑骞呭害鍊间細鏈夊眬閮ㄦ瀬鍊硷紝浜岄樁寰垎鐨勫箙搴﹀间細鍑虹幇杩囬浂鐐广傛湰鏂囦富瑕佷粙缁嶈竟缂樻娴嬩腑鐨勪竴闃跺井鍒嗙畻瀛---姊害绠楀瓙锛鍖呮嫭Roberts銆丳rewitt鍜Sobel涓夌绠楀瓙銆傛兂瑕佽绠楁搴﹀浘锛屽氨瑕佽璁℃ā鏉垮嵎绉紝棣栧厛瑕佹悶鏄庣櫧鍥惧儚鍦ㄨ绠楁椂鐨勫潗鏍囩郴锛屽緢澶氬崥鏂囧搴旂殑妯℃澘鍜屽潗鏍...
绛旓細甯歌鐨勮竟缂樻娴嬬畻瀛愭湁Roberts绠楀瓙銆丳rewitt绠楀瓙銆Sobel绠楀瓙銆丮arr-Hidreth杈圭紭妫娴嬩互鍙奵anny绠楀瓙绛夈備竴銆鍒╃敤姊害杩涜杈圭紭妫娴1銆丷oberts绠楀瓙閲囩敤瀵硅绾挎柟鍚戠浉閭讳袱鍍忕礌涔嬪樊杩戜技鐨勬搴﹀箙鍊兼潵妫娴嬭竟缂樸傝绠楀瓙瀹氫綅杈冨噯纭紝浣嗗鍣０姣旇緝鏁忔劅锛屾娴嬫按骞冲拰绔栫洿杈圭紭鏁堟灉濂戒簬鏂滃悜杈圭紭銆2銆丼obel绠楀瓙鏍规嵁鍥惧儚鐨勫儚绱犵偣涓婁笅銆...
绛旓細Sobel绠楀瓙 涓绉嶄竴闃跺井鍒绠楀瓙锛瀹鍒╃敤鍍忕礌閭昏繎鍖哄煙鐨勬搴﹀兼潵璁＄畻1涓儚绱犵殑姊害锛岀劧鍚庢牴鎹竴瀹氱殑缁濆鍊兼潵鍙栬垗銆侾rewitt绠楀瓙 Prewitt绠楀瓙鏄3*3绠楀瓙妯℃澘銆2涓嵎绉牳dx ,涓嶈褰㈡垚浜哖rewitt绠楀瓙銆備笌Sobel绠楀瓙鐨勬柟娉曚竴鏍凤紝鍥惧儚涓殑姣忎釜鐐归兘鐢ㄨ繖2涓牳杩涜鍗风Н锛屽彇鏈澶у间綔涓鸿緭鍑哄笺傚悇涓畻瀛愮殑浼樼己鐐癸細Robert...
绛旓細鏄傚鎵惧浘鍍忎腑鐨勮竟缂樻槸涓轰簡鎵惧埌鍙樺寲闈炲父寮虹儓鐨勭浉閭诲儚绱狅紝渚嬪浠0-255鎴栦粠255-0锛屽洜姝よ竟缂樻槸0銆傛暟鍊煎井鍒嗗彲浠ユ眰鍙樺寲鐜囷紝鍦ㄥ浘鍍忎笂绂绘暎鍊兼眰姊害锛屽浘鍍忓鐞嗕腑鏈夊绉嶈竟缂樻娴嬶紙姊害锛夌畻瀛愶紝甯哥敤鐨勫寘鎷櫘閫氫竴闃跺樊鍒锛孯obert绠楀瓙锛堜氦鍙夊樊鍒嗭級锛Sobel绠楀瓙锛浜岄樁鎷夋櫘鎷夋柉绠楀瓙绛夌瓑锛屾槸鍩轰簬瀵绘壘姊害寮哄害銆
