normalized cross correlation;cros correlation problem!!

1 Ansicht (letzte 30 Tage)
mehmet Söyler
mehmet Söyler am 19 Feb. 2013
I did a correlation of two different picture. I have found the same correlation with the two different objects in the picture. but it did not object to my trimmed. I shared a picture for it. What is the reason for this? I have used the following commands. > rgbImage = imread('d:/b1.jpg'); >> subplot(3, 3, 1); >> imshow(rgbImage, []); >> axis on; >> smallSubImage = imcrop(rgbImage, [55 325 80 104]); >> subplot(3, 3, 2); >> imshow(smallSubImage, []); >> axis on; >> correlationOutput = normxcorr2(smallSubImage(:,:,1), rgbImage(:,:,1)); >> subplot(3, 3, 3); >> imshow(correlationOutput, []); >> subplot(3, 3, 4); >> [maxCorrValue, maxIndex] = max(abs(correlationOutput(:))); >> [ypeak, xpeak] = ind2sub(size(correlationOutput),maxIndex(1)); >> corr_offset = [(xpeak-size(smallSubImage,2)) (ypeak-size(smallSubImage,1))]; >> subplot(3, 3, 4); >> imshow(rgbImage); >> hold on; >> rectangle('position',[corr_offset(1) corr_offset(2) 50 50],... 'edgecolor','g','linewidth',2); >> >> rgbImage = imread('d:/b2.jpg'); >> subplot(3, 3, 5); >> rgbImage1 = imread('d:/b2.jpg'); >> imshow(rgbImage1, []); >> axis on; >> correlationOutput = normxcorr2(smallSubImage(:,:,1), rgbImage1(:,:,1)); >> subplot(3, 3, 6); >> correlationOutput2 = normxcorr2(smallSubImage(:,:,1), rgbImage1(:,:,1)); >> imshow(correlationOutput2, []); >> [maxCorrValue, maxIndex] = max(abs(correlationOutput2(:))); >> [ypeak, xpeak] = ind2sub(size(correlationOutput2),maxIndex(1)); >> corr_offset = [(xpeak-size(smallSubImage,2)) (ypeak-size(smallSubImage,1))]; >> subplot(3, 3, 7); >> imshow(rgbImage1); >> hold on; >> rectangle('position',[corr_offset(1) corr_offset(2) 50 50],... 'edgecolor','g','linewidth',2); Where is my fault?.. http://img856.imageshack.us/img856/5973/memog.jpg
  1 Kommentar
Shashank Prasanna
Shashank Prasanna am 19 Feb. 2013
Can you use the '{} code' button in order to format your code. It is extremely unreadable.

Melden Sie sich an, um zu kommentieren.

Antworten (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by