To know which operators to apply and in which order, as well as attributing good values to their parameters is a challenge for users of computer vision. This paper proposes a solution to this problem as a multi-agent system modeled according to the Vowel approach and using the Q-learning algorithm to optimize its choice. An implementation is given to test and validate this method.
@article{arxiv.1311.6054,
title = {Q-learning optimization in a multi-agents system for image segmentation},
author = {Issam Qaffou and Mohamed Sadgal and Abdelaziz Elfazziki},
journal= {arXiv preprint arXiv:1311.6054},
year = {2013}
}