A Multiclass Classification Method Based on Multiple Pairwise Classifiers

	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/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Tomoyuki Hamamura Articles by Hiroyuki Mizutani Articles by Bunpei Irie

Seventh International Conference on Document Analysis and Recognition (ICDAR'03) - Volume 2

Edinburgh, Scotland

August 03-August 06

ISBN: 0-7695-1960-1

	ASCII Text	x
	Tomoyuki Hamamura, Hiroyuki Mizutani, Bunpei Irie, "A Multiclass Classification Method Based on Multiple Pairwise Classifiers," Document Analysis and Recognition, International Conference on, vol. 2, pp. 809, Seventh International Conference on Document Analysis and Recognition (ICDAR'03) - Volume 2, 2003.

	BibTex	x
	@article{ 10.1109/ICDAR.2003.1227774, author = {Tomoyuki Hamamura and Hiroyuki Mizutani and Bunpei Irie}, title = {A Multiclass Classification Method Based on Multiple Pairwise Classifiers}, journal ={Document Analysis and Recognition, International Conference on}, volume = {2}, year = {2003}, isbn = {0-7695-1960-1}, pages = {809}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICDAR.2003.1227774}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Document Analysis and Recognition, International Conference on TI - A Multiclass Classification Method Based on Multiple Pairwise Classifiers SN - 0-7695-1960-1 SP EP A1 - Tomoyuki Hamamura, A1 - Hiroyuki Mizutani, A1 - Bunpei Irie, PY - 2003 KW - null VL - 2 JA - Document Analysis and Recognition, International Conference on ER -

Tomoyuki Hamamura, Toshiba Corp

Hiroyuki Mizutani, Toshiba Corp

Bunpei Irie, Toshiba Corp

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICDAR.2003.1227774

In this paper, a new method of composing a multi-class classifier using pairwise classifiers is proposed. A "Resemblance Model" is exploited to calculate a posteriori probability for combining pairwise classifiers. We proved the validity of this model by using approximation of a posteriori probability formula. Using this theory, we can obtain the optimal decision. An experimental result of handwritten numeral recognition is presented, supporting the effectiveness of our method.

Citation:

Tomoyuki Hamamura, Hiroyuki Mizutani, Bunpei Irie, "A Multiclass Classification Method Based on Multiple Pairwise Classifiers," icdar, vol. 2, pp.809, Seventh International Conference on Document Analysis and Recognition (ICDAR'03) - Volume 2, 2003

Peer Review Notice | Give Us Feedback

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