I have obtained the image below after applying thresholding. The white areas inside the boundaries represent the defective part. I only want these defective parts on the image, like the ones inside the blue boxes. The approach in my mind is to use any edge detection algorithm and then subtract that image from the original one so that only defective parts remain on the image. I have used many edge detection algorithms, but I failed to obtain the desired result. Kindly tell me how to extract boundaries or edges from the given image. Or is there any better way to solve this problem?
Dear Umama Nasir
These links might be helpful, have a look:
1. http://vision.cs.utexas.edu/378h-spring2017/slides/lecture4-binary.pdf
2. https://stackoverflow.com/questions/49138160/detect-edge-from-binary-image-using-canny-edge-detection-from-opencv
3. https://www.mathworks.com/matlabcentral/answers/880993-how-to-detect-edges-in-binary-image
Kind Regards
Qamar Ul Islam
A better way would be to detect edges and remove 'normal' portions. then, search for groups of white pixels which seem to define the defect.
Dear Umama Nasir,
I suggest you search for Holistically Nested (HED) edge detection.
I will not answer about edge detection, I prefer to give you a piece of warning: this binarized image seems completely inappropriate to detect "defective parts". The problem should be addressed from the original image, too much information has been lost.
Hello,
You might try Hough Transform to detect rectangles in the image directly and then locate those white pixel-area in the detected rectangles to decide as defective.
It seems to be better to apply some preprocessing methods to sharpen the rectangles such as blurring, expanding, dilation, size filtering etc before Hough Transform.
Regards,
- Badges
- Science topic
- Similar topics
- Biological Science
- Biochemistry
- Biochemical Techniques
- Analytical Chemistry
- pH