I'm looking for a deep-learning based segmentation capability, which should primarily consist of two steps:

The image to be examined contains certain structures, which are mainly defined by geometric properties. For example, stripe-like structures on a grayish background. These structures are to be found with the help of this deep learning approach.

Now, in principle, a kind of rough sketch is to be drawn, for example a paint sketch of these same elongated structures.

Based on these rough sketches, the relevant, real structures are to be found and the segmentation problem is to be solved.

In the meantime I have searched for some time, if something like this possibly already exists, but have found nothing. Does anyone of you maybe know where I could find something like this (github repos ; matlab approaches).

Would be happy about every kind of help from you peoples! Thanks



You must log in to answer this question.

Browse other questions tagged .