3

I have input RGB images as follows:

enter image description here

I have a dataset of manually annotated images highlighting the outline(edges) from the input images I am attaching an example.

enter image description here

My aim is to train a ML algorithm which learns how these outlines are mapped. And when given a new image it should produce similar output. Is there any way that this can be done?

Ive tried canny-edge detector,sobel and other type of open cv transforms. But they do not distinct object from their background properly. So I am looking into ML.

Juan Esteban de la Calle
  • 2,318
  • 9
  • 28
Ajinkya
  • 235
  • 5
  • 10

1 Answers1

1

What You are seeking is called 'Edge detection' in CVML fields. In my knowledge, DexiNed is one of best models. See papers in paperswithcode.

https://paperswithcode.com/task/edge-detection

Mason Ji Ming
  • 51
  • 6