How to label shape
2 ビュー (過去 30 日間)
古いコメントを表示
if true
% code
endS = imread('test.jpg');
S = im2bw(S);
S2 = ~S;
imshow(S2);
S3 = bwlabel(S2);
imagesc(S3);
S4 = regionprops(S3,'MinorAxisLength','MajorAxisLength','Area','Perimeter','centroid');
for cnt = 1:length(S4)
score1(cnt) = abs(1-(S4(cnt).MajorAxisLength-S4(cnt).MinorAxisLength)...
/max([S4(cnt).MajorAxisLength,S4(cnt).MinorAxisLength]));
score2(cnt) = abs(1 - abs(pi*((mean([S4(cnt).MajorAxisLength,...
S4(cnt).MinorAxisLength]))/2)^2-S4(cnt).Area)/S4(cnt).Area);
score3(cnt) = abs(1 - abs(pi*(max([S4(cnt).MajorAxisLength,...
S4(cnt).MinorAxisLength]))-S4(cnt).Perimeter)/S4(cnt).Perimeter);
end
score = mean([score1;score2;score3]);
imshow(S2)
for cnt = 1:length(S4)
text(S4(cnt).Centroid(1),S4(cnt).Centroid(2),num2str(score(cnt)),'color','red');
end
how to label the output result, if the score is higher than 0.92, then the object will have label circle. i try using if-else statement, but couldnt get it work.can someone help me.thank you
1 件のコメント
Image Analyst
2014 年 4 月 11 日
You forgot to attach test.jpg. Do that and we can run your code. Also explain what "the object will have label circle" means. Do you mean you want to plot a circle in the overlay surrounding the object, or perhaps a small circle right at the centroid. And what is being computer in that long formula for score1, scroe2, and score3? Why are there no comments whatsoever in this code? ANd why is it not properly indented so that we can read it? Did you know you can type control-a and then control-i in MATLAB to fix your indenting. Then paste into the editor window here and highlight it. THEN (not before) is when you click the {}Code button. Please fix. http://www.mathworks.com/matlabcentral/answers/13205-tutorial-how-to-format-your-question-with-markup
採用された回答
Image Analyst
2014 年 4 月 11 日
Adapted from my Image Processing Tutorial: http://www.mathworks.com/matlabcentral/fileexchange/?term=authorid%3A31862
% Label regions.
labeledImage = bwlabel(binaryImage);
% Measure regions.
measurements = regionprops(labeledImage, 'area', 'perimeter');
% Convert structure fields into arrays.
allAreas = [measurements.Area];
appPerimeters = [measurements.Perimeter];
% Compute circularity. 1 = perfect circle. Higher numbers = more tortuous borders.
circularities = appPerimeters.^2 ./ (4*pi*allAreas);
% Find indexes of regions that are fairly circular.
indexesOfCircular = find(circularities < 4);
labeledImage = bwlabel(binaryImage);
% Measure regions.
measurements = regionprops(labeledImage, 'area', 'perimeter');
% Extract only the circular images from the labeled image and then binarize.
circleObjects = ismember(labeledImage , indexesOfCircular) > 0
% Can relabel and measure only circular blobs if you want.
Look into the code for a fully commented image segmentation tutorial.
その他の回答 (0 件)
参考
カテゴリ
Help Center および File Exchange で Image Processing Toolbox についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!