On Distributed Representation of Output Layer for Recognizing Japanese Kana characters Using Neural Networks

Ulm, GERMANY August 18-August 20

DOI Bookmark:

http://doi.ieeecomputersociety.org/10.1109/ICDAR.1997.620573

Fourth International Conference Docum ...

	This Article
	PURCHASE ARTICLE: $19 PDF HTML IEEE Xplore Subscribers
	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 Kanad Keeni Articles by Hiroshi Shimodaira Articles by Kenji Nakayama

	ASCII Text	x
	Kanad Keeni, Hiroshi Shimodaira, Kenji Nakayama, "On Distributed Representation of Output Layer for Recognizing Japanese Kana characters Using Neural Networks," Document Analysis and Recognition, International Conference on, pp. 600, Fourth International Conference Document Analysis and Recognition (ICDAR'97), 1997.

	BibTex	x
	@article{ 10.1109/ICDAR.1997.620573, author = {Kanad Keeni and Hiroshi Shimodaira and Kenji Nakayama}, title = {On Distributed Representation of Output Layer for Recognizing Japanese Kana characters Using Neural Networks}, journal ={Document Analysis and Recognition, International Conference on}, volume = {0}, year = {1997}, isbn = {0-8186-7898-4}, pages = {600}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICDAR.1997.620573}, 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 - On Distributed Representation of Output Layer for Recognizing Japanese Kana characters Using Neural Networks SN - 0-8186-7898-4 SP EP A1 - Kanad Keeni, A1 - Hiroshi Shimodaira, A1 - Kenji Nakayama, PY - 1997 KW - Character recognition KW - neural networks KW - local representation KW - distributive representation KW - prototype vector VL - 0 JA - Document Analysis and Recognition, International Conference on ER -

Kanad Keeni, JAIST, Hokuriku

Hiroshi Shimodaira, JAIST, Hokuriku

Kenji Nakayama, Kanazawa University

This paper presents an automatic coding scheme for representing the output layer of a neural network. Compared to local representation where the number of output unit is p, the number of output unit required for the proposed representation is close to log p. The output of seven different printers were used for evaluating the performance of the system. The proposed automatic representation gave the average recognition rate of 98.7 \% for 71 categories.

Index Terms:

Character recognition, neural networks, local representation, distributive representation, prototype vector

Citation:

Kanad Keeni, Hiroshi Shimodaira, Kenji Nakayama, "On Distributed Representation of Output Layer for Recognizing Japanese Kana characters Using Neural Networks," icdar, pp.600, Fourth International Conference Document Analysis and Recognition (ICDAR'97), 1997

Peer Review Notice | Give Us Feedback

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