area of many cracks in image

1 view (last 30 days)
Nida Aleqabie
Nida Aleqabie on 14 Jul 2019
Answered: Nida Aleqabie on 16 Jul 2019
hello
i am ask about how can find the objects in image
type of image: street image that contine crack
i need to find the crack and compute the area of each crack in image and then get Priority to the crack have big area

Accepted Answer

Image Analyst
Image Analyst on 14 Jul 2019
What I'd do is:
  1. Take a photo of a completely uniform white sheet to get a background that you can use for lens shading correction. That's why when you thresholded you had stuff from the corners and edges.
  2. Turn that image into an image where each pixel is the percentage of light that hits that pixel.
  3. Snap an image of perfect concrete and divide that image by the percentage image to create an image like you would have had, had you had an imaging system with no shading at all.
  4. Use stdfilt() to see what the normal variation is in that kind of image.
  5. Snap and background correct an image with a crack in it.
  6. Use stdfilt() on it then threshold it at a value higher than normal, because cracks and edges will have a higher standard deviation than uniform, perfect concrete.
  7. Use regionprops() on the thresholded image to make whatever measurements you want.
Attach your perfect image, your white background sheet image, and your image with a crack in it if you need help. I'm attaching a background correction demo to help you.
See my Image Segmentation Tutorial if you need help with masking, filtering, measuring, regionprops, etc.: in my File Exchange

More Answers (2)

Nida Aleqabie
Nida Aleqabie on 15 Jul 2019
thank u very much
can you help me more with asimple example
with my best wishes
  3 Comments
Nida Aleqabie
Nida Aleqabie on 15 Jul 2019
that is my perfect image with no crack

Sign in to comment.


Nida Aleqabie
Nida Aleqabie on 16 Jul 2019
plz sear mage Analyst can you help me

Community Treasure Hunt

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

Start Hunting!