Presentation	1996/12/19 New Pattern Recognition Method Based on Relationship between Subspace Method and Modified Bayes Discriminant Function Yoshiaki Kurosawa,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Theoretical relationship between Subspace Method and MBDF (Modified Bayes Discriminant Function) is described in this paper. As a result, this paper reports a new discriminant function that is obtained from the assumption of a kind of Gaussian distribution on a hyper spherical surface. This function's formula is described as a weighted Subspace Method which is similar to MBDF. Subspace Method is obtained from this function with certain approximation. Experimental results show that the proposed function has a fine recognition performance similar to MBDF.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Pattern Recognition / Subspace Method / Modified Bayes Discriminant Function / Spherical Surface
Paper #	PRMU96-104
Date of Issue

Conference Information
Committee	PRMU
Conference Date	1996/12/19(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)	New Pattern Recognition Method Based on Relationship between Subspace Method and Modified Bayes Discriminant Function
Sub Title (in English)
Keyword(1)	Pattern Recognition
Keyword(2)	Subspace Method
Keyword(3)	Modified Bayes Discriminant Function
Keyword(4)	Spherical Surface
1st Author's Name	Yoshiaki Kurosawa
1st Author's Affiliation	Toshiba Research and Development Center()
Date	1996/12/19
Paper #	PRMU96-104
Volume (vol)	vol.96
Number (no)	435
Page	pp.pp.-
#Pages	8
Date of Issue