Category-dependent elastic matching based on a linear combination of eigen-deformations

Seiichi Uchida, Hiroaki Sakoe

Research output: Contribution to journalArticle

Abstract

A new elastic image matching (EM) technique based on a category-dependent deformation model is proposed. In the deformation model, any deformation of a category is described by a linear combination of eigen-deformations, which are frequent deformation directions of the category and can be estimated statistically from the actual deformations. Experimental results on handwritten characters show that the proposed technique can attain higher recognition rates than conventional EM techniques based on the affine deformation model, which is a typical category-independent deformation model. The results also show the superiority of the proposed technique over those conventional EM techniques in computational efficiency.

Original languageEnglish
Pages (from-to)13-22
Number of pages10
JournalSystems and Computers in Japan
Volume36
Issue number5
DOIs
Publication statusPublished - May 1 2005

Fingerprint

Linear Combination
Dependent
Image matching
Image Matching
Computational efficiency
Model
Computational Efficiency
Experimental Results

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Information Systems
  • Hardware and Architecture
  • Computational Theory and Mathematics

Cite this

Category-dependent elastic matching based on a linear combination of eigen-deformations. / Uchida, Seiichi; Sakoe, Hiroaki.

In: Systems and Computers in Japan, Vol. 36, No. 5, 01.05.2005, p. 13-22.

Research output: Contribution to journalArticle

@article{0dfe09fb38f6498490843c705bb00434,
title = "Category-dependent elastic matching based on a linear combination of eigen-deformations",
abstract = "A new elastic image matching (EM) technique based on a category-dependent deformation model is proposed. In the deformation model, any deformation of a category is described by a linear combination of eigen-deformations, which are frequent deformation directions of the category and can be estimated statistically from the actual deformations. Experimental results on handwritten characters show that the proposed technique can attain higher recognition rates than conventional EM techniques based on the affine deformation model, which is a typical category-independent deformation model. The results also show the superiority of the proposed technique over those conventional EM techniques in computational efficiency.",
author = "Seiichi Uchida and Hiroaki Sakoe",
year = "2005",
month = "5",
day = "1",
doi = "10.1002/scj.20229",
language = "English",
volume = "36",
pages = "13--22",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "5",

}

TY - JOUR

T1 - Category-dependent elastic matching based on a linear combination of eigen-deformations

AU - Uchida, Seiichi

AU - Sakoe, Hiroaki

PY - 2005/5/1

Y1 - 2005/5/1

N2 - A new elastic image matching (EM) technique based on a category-dependent deformation model is proposed. In the deformation model, any deformation of a category is described by a linear combination of eigen-deformations, which are frequent deformation directions of the category and can be estimated statistically from the actual deformations. Experimental results on handwritten characters show that the proposed technique can attain higher recognition rates than conventional EM techniques based on the affine deformation model, which is a typical category-independent deformation model. The results also show the superiority of the proposed technique over those conventional EM techniques in computational efficiency.

AB - A new elastic image matching (EM) technique based on a category-dependent deformation model is proposed. In the deformation model, any deformation of a category is described by a linear combination of eigen-deformations, which are frequent deformation directions of the category and can be estimated statistically from the actual deformations. Experimental results on handwritten characters show that the proposed technique can attain higher recognition rates than conventional EM techniques based on the affine deformation model, which is a typical category-independent deformation model. The results also show the superiority of the proposed technique over those conventional EM techniques in computational efficiency.

UR - http://www.scopus.com/inward/record.url?scp=17144391429&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17144391429&partnerID=8YFLogxK

U2 - 10.1002/scj.20229

DO - 10.1002/scj.20229

M3 - Article

AN - SCOPUS:17144391429

VL - 36

SP - 13

EP - 22

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 5

ER -