In a previous paper I developed a method (using traditional computer vision techniques) to add "spot colour" to images: http://users.cs.cf.ac.uk/Paul.Rosin/resources/papers/spot-CAe.pdf That is, colour is added to region (or regions) of a black and white image to make it look more attractive or interesting.

The aim of this project is to tackle this problem, but using the power of deep learning!