A Survey of Elastic Matching Techniques for Handwritten Character Recognition(Character Recognition, <Special Section>Document Image Understanding and Digital Documents)
スポンサーリンク
概要
- 論文の詳細を見る
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.
- 社団法人電子情報通信学会の論文
- 2005-08-01
著者
-
Uchida Seiichi
Kyushu Univ. Fukuoka‐shi
-
Uchida Seiichi
Faculty Of Information Science And Electrical Engineering Kyushu University
-
SAKOE Hiroaki
Faculty of Information Science and Electrical Engineering, Kyushu University
-
Sakoe Hiroaki
Faculty Of Engineering Kyushu University
-
Sakoe Hiroaki
Kyushu Univ. Fukuoka Jpn
関連論文
- Is quantity better than quality?: a study case on a simple classifier applied to digit character recognition (パターン認識・メディア理解)
- Is quantity better than quality?: a study case on a simple classifier applied to digit character recognition (情報論的学習理論と機械学習)
- A Survey of Elastic Matching Techniques for Handwritten Character Recognition(Character Recognition, Document Image Understanding and Digital Documents)
- One Dimensional-Two Dimensional Dynamic Programming Matching Algorithm for Character Recognition
- Nonuniform Slant Correction for Handwritten Word Recognition(Image Recognition, Computer Vision)
- Better Decision Boundary for Pattern Recognition with Supplementary Information(Pattem Recognition)
- Skew Estimation by Parts