A Reinforcement Learning Framework for Parameter Control in Computer Vision Applications

CC
CRV
2004
1st Canadian Conference on Computer and Robot Vision (CRV'04)
Abstract - A Reinforcement Learning Framework for Parameter Control in Computer Vision Applications

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Graham W. Taylor

1st Canadian Conference on Computer and Robot Vision (CRV'04)

University of Western Ontario, London, Ontario, Canada

May 17-May 19

ISBN: 0-7695-2127-4

	ASCII Text	x
	Graham W. Taylor, "A Reinforcement Learning Framework for Parameter Control in Computer Vision Applications," Computer and Robot Vision, Canadian Conference, pp. 496-503, 1st Canadian Conference on Computer and Robot Vision (CRV'04), 2004.

	BibTex	x
	@article{ 10.1109/CCCRV.2004.1301489, author = {Graham W. Taylor}, title = {A Reinforcement Learning Framework for Parameter Control in Computer Vision Applications}, journal ={Computer and Robot Vision, Canadian Conference}, volume = {0}, year = {2004}, isbn = {0-7695-2127-4}, pages = {496-503}, doi = {http://doi.ieeecomputersociety.org/10.1109/CCCRV.2004.1301489}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Computer and Robot Vision, Canadian Conference TI - A Reinforcement Learning Framework for Parameter Control in Computer Vision Applications SN - 0-7695-2127-4 SP496 EP503 A1 - Graham W. Taylor, PY - 2004 KW - null VL - 0 JA - Computer and Robot Vision, Canadian Conference ER -

Graham W. Taylor, University of Waterloo

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CCCRV.2004.1301489

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.

Citation:

Graham W. Taylor, "A Reinforcement Learning Framework for Parameter Control in Computer Vision Applications," crv, pp.496-503, 1st Canadian Conference on Computer and Robot Vision (CRV'04), 2004

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.