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