Can anyone tell me how to extract and crop the roi based on its gray level profile?
Show older comments
I have taken up following steps after detection of a refernce axis using hough lines.. detected the profile (using improfile function) stored the x, y coordinates in arrays vth corresponding value of intensity profile for each co-ordinate pair using a for loop.
now i want to extract the regions having regional maxima-minima-maxima in gray level profile. then i want to crop the extracted roi. I am a new to image processing so kindly guide step by step.
Answers (1)
Image Analyst
on 11 Jan 2013
Try imregionalmax() and imregionalmin(). See my image segmentation tutorial to learn how to find objects based on their intensity and crop them into new sub-images.
If you want to identify stretches of your 1D intensity profile vector obtained from improfile(), you can use thresholding:
aboveThreshold = yourProfileArray > someThresholdValue;
Not sure why you'd want to extract stretches of that 1D vector into individual short vectors, but if you tell me why, I'll tell you how to do it, or tell you how to do what you want to do without doing extracting sub-lines.
5 Comments
Richa Nayak
on 13 Jan 2013
Image Analyst
on 13 Jan 2013
I do guide you. Have you actually run the tutorial yet? When you do you'll see how I do exactly what you ask: cropping a rectangle around objects above a threshold. If you ran my tutorial and did not have it continue on to that part, then please do so. If the cropping I did is not what you want, then explain in more detail, preferably with images to illustrate your challenging situation.
Richa Nayak
on 18 Jan 2013
Image Analyst
on 18 Jan 2013
It would have been best if you had posted these images at the beginning (please do so next time so we don't waste 7 days in getting you an answer). You need to use watershed segmentation. See these for help:
Richa Nayak
on 18 Jan 2013
Categories
Find more on Read, Write, and Modify Image in Help Center and File Exchange
Products
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!