Eigen-deformations for elastic matching based handwritten character recognition

Seiichi Uchida; Hiroaki Sakoe

doi:10.1016/S0031-3203(03)00039-6

Eigen-deformations for elastic matching based handwritten character recognition

Seiichi Uchida, Hiroaki Sakoe

Real world robotics

Research output: Contribution to journal › Article › peer-review

23 Citations (Scopus)

Abstract

Deformations in handwritten characters have category-dependent tendencies. In this paper, the estimation and the utilization of such tendencies called eigen-deformations are investigated for the better performance of elastic matching based handwritten character recognition. The eigen-deformations are estimated by the principal component analysis of actual deformations automatically collected by the elastic matching. From experimental results it was shown that typical deformations of each category can be extracted as the eigen-deformations. It was also shown that the recognition performance can be improved significantly by using the eigen-deformations for the detection of overfitting, which is the main cause of the misrecognition in the elastic matching based recognition methods.

Original language	English
Pages (from-to)	2031-2040
Number of pages	10
Journal	Pattern Recognition
Volume	36
Issue number	9
DOIs	https://doi.org/10.1016/S0031-3203(03)00039-6
Publication status	Published - Sept 2003

All Science Journal Classification (ASJC) codes

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1016/S0031-3203(03)00039-6

Cite this

@article{2b92fbd58b5840689675ea2be2341a97,

title = "Eigen-deformations for elastic matching based handwritten character recognition",

abstract = "Deformations in handwritten characters have category-dependent tendencies. In this paper, the estimation and the utilization of such tendencies called eigen-deformations are investigated for the better performance of elastic matching based handwritten character recognition. The eigen-deformations are estimated by the principal component analysis of actual deformations automatically collected by the elastic matching. From experimental results it was shown that typical deformations of each category can be extracted as the eigen-deformations. It was also shown that the recognition performance can be improved significantly by using the eigen-deformations for the detection of overfitting, which is the main cause of the misrecognition in the elastic matching based recognition methods.",

author = "Seiichi Uchida and Hiroaki Sakoe",

note = "Funding Information: The authors thank the Electrotechnical Laboratory for providing us ETL6. This work was supported in part by The Ministry of Education, Culture, Sports, Science and Technology in Japan under a Grant-in-Aid for Scientific Research No. 14780293. A preliminary version of this paper has been presented in the proceeding of ICPR2002. ",

year = "2003",

month = sep,

doi = "10.1016/S0031-3203(03)00039-6",

language = "English",

volume = "36",

pages = "2031--2040",

journal = "Pattern Recognition",

issn = "0031-3203",

publisher = "Elsevier Limited",

number = "9",

}

TY - JOUR

T1 - Eigen-deformations for elastic matching based handwritten character recognition

AU - Uchida, Seiichi

AU - Sakoe, Hiroaki

N1 - Funding Information: The authors thank the Electrotechnical Laboratory for providing us ETL6. This work was supported in part by The Ministry of Education, Culture, Sports, Science and Technology in Japan under a Grant-in-Aid for Scientific Research No. 14780293. A preliminary version of this paper has been presented in the proceeding of ICPR2002.

PY - 2003/9

Y1 - 2003/9

N2 - Deformations in handwritten characters have category-dependent tendencies. In this paper, the estimation and the utilization of such tendencies called eigen-deformations are investigated for the better performance of elastic matching based handwritten character recognition. The eigen-deformations are estimated by the principal component analysis of actual deformations automatically collected by the elastic matching. From experimental results it was shown that typical deformations of each category can be extracted as the eigen-deformations. It was also shown that the recognition performance can be improved significantly by using the eigen-deformations for the detection of overfitting, which is the main cause of the misrecognition in the elastic matching based recognition methods.

AB - Deformations in handwritten characters have category-dependent tendencies. In this paper, the estimation and the utilization of such tendencies called eigen-deformations are investigated for the better performance of elastic matching based handwritten character recognition. The eigen-deformations are estimated by the principal component analysis of actual deformations automatically collected by the elastic matching. From experimental results it was shown that typical deformations of each category can be extracted as the eigen-deformations. It was also shown that the recognition performance can be improved significantly by using the eigen-deformations for the detection of overfitting, which is the main cause of the misrecognition in the elastic matching based recognition methods.

UR - http://www.scopus.com/inward/record.url?scp=0038347410&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038347410&partnerID=8YFLogxK

U2 - 10.1016/S0031-3203(03)00039-6

DO - 10.1016/S0031-3203(03)00039-6

M3 - Article

AN - SCOPUS:0038347410

SN - 0031-3203

VL - 36

SP - 2031

EP - 2040

JO - Pattern Recognition

JF - Pattern Recognition

IS - 9

ER -

Eigen-deformations for elastic matching based handwritten character recognition

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this