I'm trying to implement a solution in python to detect skin in an image.

I'm evaluating the Mask R-CNN model to create a mask on the skin (not on clothes). The problem is that every solution I have encountered using Mask R-CNN uses it to classify objects. I'm afraid that using it trying to classify texture might be a problem. Is it the case?

My dataset is actually pretty good, composed of the

  1. original image,
  2. precise mask on the skin, and
  3. grounding box.

Can I use a Mask R-CNN to detect a skin texture?



You must log in to answer this question.

Browse other questions tagged .