Presentation 2003/3/6
Handwritten Numeral Recognition by Mirror Image Learning for Autoassociative Neural Networks
Shusaku SHIMIZU, Wataru OHYAMA, Tetsushi WAKABAYASHI, Fumitaka KIMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper studies on the mirror image learning algorithm for the autoassociative neural networks and evaluates the performance by handwritten numeral recognition test. Each of the autoassociative networks is first trained independently for each class using the feature vector of the class. Then the mirror image learning algorithm is applied to enlarge the learning sample of each class by mirror image patterns of the confusing classes to achieve higher recognition accuracy. Recognition accuracy of the autoassociative neural network classifier was improved by the mirror image learning from 98.76% to 99.23% in the recognition test for handwritten numeral database IPTP CD-ROM1[1].
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / autoassociative neural network / corrective learning / mirror image learning
Paper # PRMU2002-233
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/3/6(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Handwritten Numeral Recognition by Mirror Image Learning for Autoassociative Neural Networks
Sub Title (in English)
Keyword(1) neural network
Keyword(2) autoassociative neural network
Keyword(3) corrective learning
Keyword(4) mirror image learning
1st Author's Name Shusaku SHIMIZU
1st Author's Affiliation Faculty of Engineering, Mie University()
2nd Author's Name Wataru OHYAMA
2nd Author's Affiliation Faculty of Engineering, Mie University
3rd Author's Name Tetsushi WAKABAYASHI
3rd Author's Affiliation Faculty of Engineering, Mie University
4th Author's Name Fumitaka KIMURA
4th Author's Affiliation Faculty of Engineering, Mie University
Date 2003/3/6
Paper # PRMU2002-233
Volume (vol) vol.102
Number (no) 707
Page pp.pp.-
#Pages 5
Date of Issue