This paper presents a survey of elastic matching (EM) techniques employed in handwritten character recognition. EM is often called deformable template, flexible matching, or nonlinear template matching, and defined as the optimization problem of two-dimensional warping (2DW) which specifies the pixel-to-pixel correspondence between two subjected character image patterns. The pattern distance evaluated under optimized 2DW is invariant to a certain range of geometric deformations. Thus, by using the EM distance as a discriminant function, recognition systems robust to the deformations of handwritten characters can be realized. In this paper, EM techniques are classified according to the type of 2DW and the properties of each class are outlined. Several topics around EM, such as the category-dependent deformation tendency of handwritten characters, are also discussed.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Seiichi UCHIDA, Hiroaki SAKOE, "A Survey of Elastic Matching Techniques for Handwritten Character Recognition" in IEICE TRANSACTIONS on Information,
vol. E88-D, no. 8, pp. 1781-1790, August 2005, doi: 10.1093/ietisy/e88-d.8.1781.
Abstract: This paper presents a survey of elastic matching (EM) techniques employed in handwritten character recognition. EM is often called deformable template, flexible matching, or nonlinear template matching, and defined as the optimization problem of two-dimensional warping (2DW) which specifies the pixel-to-pixel correspondence between two subjected character image patterns. The pattern distance evaluated under optimized 2DW is invariant to a certain range of geometric deformations. Thus, by using the EM distance as a discriminant function, recognition systems robust to the deformations of handwritten characters can be realized. In this paper, EM techniques are classified according to the type of 2DW and the properties of each class are outlined. Several topics around EM, such as the category-dependent deformation tendency of handwritten characters, are also discussed.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e88-d.8.1781/_p
Copy
@ARTICLE{e88-d_8_1781,
author={Seiichi UCHIDA, Hiroaki SAKOE, },
journal={IEICE TRANSACTIONS on Information},
title={A Survey of Elastic Matching Techniques for Handwritten Character Recognition},
year={2005},
volume={E88-D},
number={8},
pages={1781-1790},
abstract={This paper presents a survey of elastic matching (EM) techniques employed in handwritten character recognition. EM is often called deformable template, flexible matching, or nonlinear template matching, and defined as the optimization problem of two-dimensional warping (2DW) which specifies the pixel-to-pixel correspondence between two subjected character image patterns. The pattern distance evaluated under optimized 2DW is invariant to a certain range of geometric deformations. Thus, by using the EM distance as a discriminant function, recognition systems robust to the deformations of handwritten characters can be realized. In this paper, EM techniques are classified according to the type of 2DW and the properties of each class are outlined. Several topics around EM, such as the category-dependent deformation tendency of handwritten characters, are also discussed.},
keywords={},
doi={10.1093/ietisy/e88-d.8.1781},
ISSN={},
month={August},}
Copy
TY - JOUR
TI - A Survey of Elastic Matching Techniques for Handwritten Character Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1781
EP - 1790
AU - Seiichi UCHIDA
AU - Hiroaki SAKOE
PY - 2005
DO - 10.1093/ietisy/e88-d.8.1781
JO - IEICE TRANSACTIONS on Information
SN -
VL - E88-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2005
AB - This paper presents a survey of elastic matching (EM) techniques employed in handwritten character recognition. EM is often called deformable template, flexible matching, or nonlinear template matching, and defined as the optimization problem of two-dimensional warping (2DW) which specifies the pixel-to-pixel correspondence between two subjected character image patterns. The pattern distance evaluated under optimized 2DW is invariant to a certain range of geometric deformations. Thus, by using the EM distance as a discriminant function, recognition systems robust to the deformations of handwritten characters can be realized. In this paper, EM techniques are classified according to the type of 2DW and the properties of each class are outlined. Several topics around EM, such as the category-dependent deformation tendency of handwritten characters, are also discussed.
ER -