Mirror image learning for autoassociative neural networks

Shusaku Shimizu, Wataru Oyama, Tetsushi Wakabayashi, Fumitaka Kimura

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

1 被引用数 (Scopus)

抄録

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].

本文言語英語
ホスト出版物のタイトルProceedings - 7th International Conference on Document Analysis and Recognition, ICDAR 2003
出版社IEEE Computer Society
ページ804-808
ページ数5
ISBN(電子版)0769519601
DOI
出版ステータス出版済み - 1 1 2003
イベント7th International Conference on Document Analysis and Recognition, ICDAR 2003 - Edinburgh, 英国
継続期間: 8 3 20038 6 2003

出版物シリーズ

名前Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
2003-January
ISSN(印刷版)1520-5363

その他

その他7th International Conference on Document Analysis and Recognition, ICDAR 2003
国/地域英国
CityEdinburgh
Period8/3/038/6/03

All Science Journal Classification (ASJC) codes

  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Mirror image learning for autoassociative neural networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル