Presentation 2001/12/14
Feature Extractions by realizing the topology preservation
Takanori KUROMATSU, Masayuki KASHIMA, Takayasu FUCHIDA, Sadayuki MURASHIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Kohonen Network has been presented as a self-organized feature map to realize the topology preservation between input and output and has been applied to feature extractions in various fields of applications. The topology Representing Network presented by Martinez et al has the same object as the Kohonen Network has been changed so that the topological structure is determined adaptively instead that it is determined beforehand. The feature of input data is considered to be given by the masked Delaunay triangulation and the topology preservation is attained by realizing the masked Delaunay Triangulation of input data coincides with the output shape of the feature extractor. This paper explains the fact the realization of topology preservation means the feature extraction.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Kohonen Network / Topology Representing Network / rate of topology preservation / feature extraction
Paper # PRMU2001-178
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/12/14(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Feature Extractions by realizing the topology preservation
Sub Title (in English)
Keyword(1) Kohonen Network
Keyword(2) Topology Representing Network
Keyword(3) rate of topology preservation
Keyword(4) feature extraction
1st Author's Name Takanori KUROMATSU
1st Author's Affiliation Department of Information and Computer Science, Faculty of Engineering, Kagoshima University()
2nd Author's Name Masayuki KASHIMA
2nd Author's Affiliation Department of Information and Computer Science, Faculty of Engineering, Kagoshima University
3rd Author's Name Takayasu FUCHIDA
3rd Author's Affiliation Department of Information and Computer Science, Faculty of Engineering, Kagoshima University
4th Author's Name Sadayuki MURASHIMA
4th Author's Affiliation Department of Information and Computer Science, Faculty of Engineering, Kagoshima University
Date 2001/12/14
Paper # PRMU2001-178
Volume (vol) vol.101
Number (no) 525
Page pp.pp.-
#Pages 7
Date of Issue