Detection / Identification of a curve in an image

Question

Muskan Agrawal 2020-5-23

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/530843-detection-identification-of-a-curve-in-an-image

回答： Muskan Agrawal 2020-5-26

Well I need help in how to identify a curve in image.

Like we can use hough transform for lines and circles. Is there any function, which I can use for this purpose. I am attaching an image on which I have to work.

Please do help. The image has curves which I have to detect.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Image Analyst 2020-5-23

3
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/530843-detection-identification-of-a-curve-in-an-image#answer_437128

Call bwlabel() to give each curve it's own unique ID number.

2 个评论
显示无隐藏无

Muskan Agrawal 2020-5-26

Thank you so much for your help. I continued with using bwselect. However, in it i had to manually pick up points of the curve that I want to be identified.

Could you please help me with any function which is used for identification of curves. Like houh transfor gives me an identified line or hough tranform for circles marks the circle in the given range.

It would be great if you could help with this.

Image Analyst 2020-5-26

在 MATLAB Online 中打开

You shouldn't have to do it manually with bwselect. bwlabel() does it for you. Look:

grayImage = imread('image.jpeg');
binaryImage = grayImage(:,:,1) > 200;
% Crop off huge white frame surrounding the image.
binaryImage = binaryImage(46:1058, 1094:1295);
subplot(1, 2, 1);
imshow(binaryImage);
fontSize = 15;
title('Binary Image', 'FontSize', fontSize);
% Label each blob with 8-connectivity, so we can make measurements of it
[labeledImage, numberOfBlobs] = bwlabel(binaryImage, 8);
% Apply a variety of pseudo-colors to the regions.
coloredLabelsImage = label2rgb (labeledImage, 'hsv', 'k', 'shuffle');
% Display the pseudo-colored image.
subplot(1, 2, 2);
imshow(coloredLabelsImage);
title('Labeled Image', 'FontSize', fontSize);
impixelinfo
% Get all the blob properties.  Can only pass in originalImage in version R2008a and later.
blobMeasurements = regionprops(labeledImage, 'all');
numberOfBlobs = size(blobMeasurements, 1);

See, each individually colored connected region is one blob.

To get a histogram of orientations, do this:

allOrientations = [blobMeasurements.Orientation];
figure
numBins = 180;
histogram(allOrientations, numBins);
caption = sprintf('Histogram of %d Orientations', numberOfBlobs);
title(caption, 'FontSize', fontSize);
grid on;