Presentation 1993/12/14
Character pattern recognize system using neural network with feature extraction function
Hisao Uemoto, Masaru Kakuma, Toshihide Kitama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Three recognition systems using multilayer neural network are proporsed that can recognize alphanumerical character.These systems are combined with good pattern classification ability of multilayer neural network and the feature extraction function of neocognitron.The first system can extract the pattern feature by a learning algorithm.The second system can extract the pattern feature by circuit logic.The third system is similar to the second system but differs from the numbers of feature classification. These systems were implemented and tested using alphanumerical characters.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / neocognition / pattern recognition / feature extraction
Paper # NC93-61
Date of Issue

Conference Information
Committee NC
Conference Date 1993/12/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Character pattern recognize system using neural network with feature extraction function
Sub Title (in English)
Keyword(1) neural network
Keyword(2) neocognition
Keyword(3) pattern recognition
Keyword(4) feature extraction
1st Author's Name Hisao Uemoto
1st Author's Affiliation Department of information engineering,Faculty of engineering, Kanazawa Institute of technology()
2nd Author's Name Masaru Kakuma
2nd Author's Affiliation Department of information engineering,Faculty of engineering, Kanazawa Institute of technology
3rd Author's Name Toshihide Kitama
3rd Author's Affiliation NEC Corporation
Date 1993/12/14
Paper # NC93-61
Volume (vol) vol.93
Number (no) 376
Page pp.pp.-
#Pages 8
Date of Issue