Presentation 1997/3/18
Adaptive Normalization of Handwritten Characters Using GAT/LAT
Toru WAKAHAMRA, Kazumi ODAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Conventional normalization methods for handwritten characters have limitations as preprocessing operations because they are category-independent. This paper introduces an adaptive or category-dependent normalization method that normalizes an input pattern against each reference pattern using global and local affine transformation(GAT/LAT) in a hierarchical manner as a general deformation model. Experiments using input patterns of 3,171 categories, including Kanji, Kana, and alphanumerics, written by 36 people in the cursive style and the square-style reference patterns have shown not only that the proposed method can absorb a fair large amount of distortion within the same category but also that discrimination ability is greatly improved by the suppression of excessive normalization against similarly shaped but different categories.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Adaptive normalization / deformation model / global/local affine transformation / weighted least-squares method
Paper # PRMU96-186
Date of Issue

Conference Information
Committee PRMU
Conference Date 1997/3/18(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) Adaptive Normalization of Handwritten Characters Using GAT/LAT
Sub Title (in English)
Keyword(1) Adaptive normalization
Keyword(2) deformation model
Keyword(3) global/local affine transformation
Keyword(4) weighted least-squares method
1st Author's Name Toru WAKAHAMRA
1st Author's Affiliation NTT Human Interface Laboratories()
2nd Author's Name Kazumi ODAKA
2nd Author's Affiliation NTT Human Interface Laboratories
Date 1997/3/18
Paper # PRMU96-186
Volume (vol) vol.96
Number (no) 598
Page pp.pp.-
#Pages 8
Date of Issue