Presentation 1998/6/18
Pattern Recognition Method for Metric Space by Four Points Embedding
Hideya YOSHIUCHI, Koji TSUDA, Michihiko MINOH,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In solving pattern recognition problem on Euclidean space, prototypes, which represent classes, are defined. On the other hand in solving it on metric space, Nearest Neighbour and K-Nearest Neighbour are frequently used, in which no prototype is defined. In this paper, we propose a new pattern recognition method for metric space that can use the centroid of three patterns in a class. This method is based on the theorem that four points of any metric space can be embedded into Euclidean space by an appropriate metric transform.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) metric space / Nearest Neighbour / embedding / pattern recognition
Paper # PRMU98-29
Date of Issue

Conference Information
Committee PRMU
Conference Date 1998/6/18(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) Pattern Recognition Method for Metric Space by Four Points Embedding
Sub Title (in English)
Keyword(1) metric space
Keyword(2) Nearest Neighbour
Keyword(3) embedding
Keyword(4) pattern recognition
1st Author's Name Hideya YOSHIUCHI
1st Author's Affiliation Graduate School of Informatics, Kyoto University()
2nd Author's Name Koji TSUDA
2nd Author's Affiliation Electrotechnical Laboratory
3rd Author's Name Michihiko MINOH
3rd Author's Affiliation Center for Information and Multimedia Studies, Kyoto University
Date 1998/6/18
Paper # PRMU98-29
Volume (vol) vol.98
Number (no) 126
Page pp.pp.-
#Pages 8
Date of Issue