London, ON, Canada
May 17, 2004 to May 19, 2004
We propose a framework for solving the parameter selection problem for computer vision applications using reinforcement learning agents. Connectionist-based function approximation is employed to reduce the state space. Automatic determination of fuzzy membership functions is stated as a specific case of the parameter selection problem. Entropy of a fuzzy event is used as a reinforcement. We have carried out experiments to generate brightness membership functions for several images. The results show that the reinforcement learning approach is superior to an existing simulated annealing-based approach.
Learning, Computer vision, Application software, State-space methods, Simulated annealing, Filters, Pattern analysis, Machine intelligence, Laboratories, Function approximation
"A reinforcement learning framework for parameter control in computer vision applications", CCCRV, 2004, Proceedings First Canadian Conference on Computer and Robot Vision, Proceedings First Canadian Conference on Computer and Robot Vision 2004, pp. 496-503, doi:10.1109/CCCRV.2004.1301489