Presentation	2007-03-16 Filter Mask Learning for Feature Extraction in Similar Pattern Discrimination Yoshiaki KUROSAWA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Similar pattern discrimination is an important subject in the pattern recognition field. The experiments for this subject was executed and examined with the method which had been introduced with MCE/GPD, called as DFE to determine adequate parameters automatically in a recognition system. The learning target of this method is filters in a feature extraction unit. As the result, the filters which emphasize the difference between similar characters were created and the recognition accuracy was improved.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	probabilistic descent / OCR / feature extraction / learning / MCE / GPD
Paper #	PRMU2006-267
Date of Issue

Conference Information
Committee	PRMU
Conference Date	2007/3/9(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)	Filter Mask Learning for Feature Extraction in Similar Pattern Discrimination
Sub Title (in English)
Keyword(1)	probabilistic descent
Keyword(2)	OCR
Keyword(3)	feature extraction
Keyword(4)	learning
Keyword(5)	MCE
Keyword(6)	GPD
1st Author's Name	Yoshiaki KUROSAWA
1st Author's Affiliation	Toshiba Solutions Corporation Fuchu Engineering Center()
Date	2007-03-16
Paper #	PRMU2006-267
Volume (vol)	vol.106
Number (no)	606
Page	pp.pp.-
#Pages	6
Date of Issue