Presentation 1998/2/19
A Fundamental Study on Handwritten Character Recognition Using Displacement Extraction
Yoshiki Mizukami,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This report describes a fundamental contrastive study of two handwritten Character recognition methods. In the first method (Pixel-based method), the displacement between an input pattern and a template pattern is extracted based on the pixel intensity value on each image. In the second method (Feature-based method), the displacement is extracted based on directional features derived from the images. Several experiments were conducted using NIST Special Database 19. The results show that the introduction of displacement extraction is more effective in Pixel-based method than in Feature-based method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) handwritten character recognition / displacement extraction / directional feature / regularization
Paper #
Date of Issue

Conference Information
Committee PRMU
Conference Date 1998/2/19(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) A Fundamental Study on Handwritten Character Recognition Using Displacement Extraction
Sub Title (in English)
Keyword(1) handwritten character recognition
Keyword(2) displacement extraction
Keyword(3) directional feature
Keyword(4) regularization
1st Author's Name Yoshiki Mizukami
1st Author's Affiliation Faculty of Engineering, Yamaguchi University()
Date 1998/2/19
Paper #
Volume (vol) vol.97
Number (no) 558
Page pp.pp.-
#Pages 8
Date of Issue