Handwritten character recognition using elastic matching based on a class-dependent deformation model

Authors:
Seiichi Uchida;Hiroaki Sakoe
Affiliations:
-;-
Venue:
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Year:
2003

Citing 2
Cited 4

Active shape models—their training and application

Computer Vision and Image Understanding
Efficient Pattern Recognition Using a New Transformation Distance

Advances in Neural Information Processing Systems 5, [NIPS Conference]

Online Character Recognition Based on Elastic Matching and Quadratic Discrimination

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Handwritten character recognition using elastic matching and PCA

Proceedings of the International Conference on Advances in Computing, Communication and Control
Sparse representation based on K-nearest neighbor classifier for degraded Chinese character recognition

PCM'10 Proceedings of the Advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II
Recognition of very low-resolution characters from motion images captured by a portable digital camera

PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

For handwritten character recognition, a new elastic imagematching (EM) technique based on a class-dependentdeformation model is proposed. In the deformation model,any deformation of a class is described by a linear combinationof eigen-deformations, which are intrinsic deformationdirections of the class. The eigen-deformations canbe estimated statistically from the actual deformations ofhandwritten characters. Experimental results show that theproposed technique can attain higher recognition rates thanconventional EM techniques based on class-independentdeformation models. The results also show the superiorityof the proposed technique over those conventional EMtechniques in computational efficiency.