Revision history [back]

I could think of training a neural network, probably a conv net, to detect the area but I'm quite new to opencv and i don't know how to retrieve the area afterwards.

First of all, OpenCV does not support convnet training, just loading existing models and processing them.

That being said, if your not more specific to your application, then we cannot pass you a solution. Simply because there are tons of segmentation approaches out there.