A Reinforcement Learning Framework for Parameter Control in Computer Vision Applications

Authors:
Affiliations:
Venue:
CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
Year:
2004

Citing 6
Cited 1

Automatically determine the membership function based on the maximum entropy principle

Information Sciences: an International Journal
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Maximum entropy-based optimal threshold selection using deterministic reinforcement learning with controlled randomization

Signal Processing
Reinforcement Learning Agents

Artificial Intelligence Review
Feedforward Neural Networks in Reinforcement Learning Applied to High-Dimensional Motor Control

ALT '02 Proceedings of the 13th International Conference on Algorithmic Learning Theory
Reinforcement learning: a survey

Journal of Artificial Intelligence Research

Selecting vision operators and fixing their optimal parameters values using reinforcement learning

ICISP'12 Proceedings of the 5th international conference on Image and Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a framework for solving the parameter selectionproblem for computer vision applications using reinforcementlearning agents. Connectionist-based functionapproximation is employed to reduce the state space. Automaticdetermination of fuzzy membership functions is statedas a specific case of the parameter selection problem. Entropyof a fuzzy event is used as a reinforcement. We havecarried out experiments to generate brightness membershipfunctions for several images. The results show that the reinforcementlearning approach is superior to an existing simulatedannealing-based approach.