Feature extraction for handwritten chinese character by weighted dynamic mesh based on nonlinear normalization

Authors:
Guang Chen;Hong-Gang Zhang;Jun Guo
Affiliations:
Beijing University of Posts and Telecommunications, Beijing;Beijing University of Posts and Telecommunications, Beijing;Beijing University of Posts and Telecommunications, Beijing
Venue:
ICAPR'05 Proceedings of the Third international conference on Advances in Pattern Recognition - Volume Part I
Year:
2005

Citing 3
Cited 0

A nonlinear normalization method for handprinted Kanji character recognition—line density equalization

Pattern Recognition
Introduction to statistical pattern recognition (2nd ed.)

Introduction to statistical pattern recognition (2nd ed.)
A Handwritten Character Recognition System Using Directional Element Feature and Asymmetric Mahalanobis Distance

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a new feature extraction method contributing to improvement of the performance of a handwritten Chinese character recognition system. By using enhanced weighted dynamic meshes based on nonlinear normalization, this method not only avoids the zigzags and other undesirable side effects introduced in the original Yamada et al.'s nonlinear normalization method but also avoids additional feature normalization process in the original Lian-Wen Jin et al.'s and WU Tian-lei et al.'s dynamic mesh method. Experiment on HCL2000, a handwritten Chinese character database, shows that our method achieves superior performance.