Presentation 2012-05-29
Iterative Discriminant Analysis in Non-linear Space
Yohei Takeuchi, Momoyo Ito, Minoru Fukumi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In pattern recognition, Fisher Linear Discriminant Analysis (FLDA) is one of the most effective feature extraction methods. Recently, FLDA has been improved in various ways and Simple-FLDA (SFLDA) has been proposed by Fukumi et al., which is capable of obtaining an eigenspace spanned by eigenvectors with simple iterative calculations. However, it might be not effective in cases where complex datasets are used. In this paper, we propose non-linear discriminant analysis, which is expanded SFLDA for more effective classification. In the classification experiment, features obtained by the proposed method is superior than SFLDA features for classification with each of datasets.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Pattern Recognition / Feature Extraction / Discriminant Analysis / Kernel Method
Paper # NLP2012-37
Date of Issue

Conference Information
Committee NLP
Conference Date 2012/5/21(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 Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Iterative Discriminant Analysis in Non-linear Space
Sub Title (in English)
Keyword(1) Pattern Recognition
Keyword(2) Feature Extraction
Keyword(3) Discriminant Analysis
Keyword(4) Kernel Method
1st Author's Name Yohei Takeuchi
1st Author's Affiliation Graduate School of Advanced Technology and Science, The University of Tokushima()
2nd Author's Name Momoyo Ito
2nd Author's Affiliation Graduate School of Advanced Technology and Science, The University of Tokushima
3rd Author's Name Minoru Fukumi
3rd Author's Affiliation Graduate School of Advanced Technology and Science, The University of Tokushima
Date 2012-05-29
Paper # NLP2012-37
Volume (vol) vol.112
Number (no) 69
Page pp.pp.-
#Pages 6
Date of Issue