A robust model for on-line handwritten japanese text recognition

Authors:
Bilan Zhu;Xiang-Dong Zhou;Cheng-Lin Liu;Masaki Nakagawa
Affiliations:
Tokyo University of Agriculture and Technology (TUAT), Department of Computer Science, 184-8588, Tokyo, Japan;Tokyo University of Agriculture and Technology (TUAT), Department of Computer Science, 184-8588, Tokyo, Japan;Institute of Automation, Chinese Academy of Sciences, National Laboratory of Pattern Recognition (NLPR), 100190, Beijing, China;Tokyo University of Agriculture and Technology (TUAT), Department of Computer Science, 184-8588, Tokyo, Japan
Venue:
International Journal on Document Analysis and Recognition - Special Issue DRR09
Year:
2010

Citing 0
Cited 8

Exam script analysis from a pen and paper device

ITHET'10 Proceedings of the 9th international conference on Information technology based higher education and training
An approach for real-time recognition of online Chinese handwritten sentences

Pattern Recognition
Attention-Feedback Based Robust Segmentation of Online Handwritten Isolated Tamil Words

ACM Transactions on Asian Language Information Processing (TALIP)
Hindi handwritten word recognition using HMM and symbol tree

Proceeding of the workshop on Document Analysis and Recognition
A robust method for coarse classifier construction from a large number of basic recognizers for on-line handwritten Chinese/Japanese character recognition

Pattern Recognition
Building compact recognizer with recognition rate maintained for on-line handwritten Japanese text recognition

Pattern Recognition Letters
Building a compact online MRF recognizer for large character set by structured dictionary representation and vector quantization technique

Pattern Recognition
Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a robust context integration model for on-line handwritten Japanese text recognition. Based on string class probability approximation, the proposed method evaluates the likelihood of candidate segmentation–recognition paths by combining the scores of character recognition, unary and binary geometric features, as well as linguistic context. The path evaluation criterion can flexibly combine the scores of various contexts and is insensitive to the variability in path length, and so, the optimal segmentation path with its string class can be effectively found by Viterbi search. Moreover, the model parameters are estimated by the genetic algorithm so as to optimize the holistic string recognition performance. In experiments on horizontal text lines extracted from the TUAT Kondate database, the proposed method achieves the segmentation rate of 0.9934 that corresponds to a f-measure and the character recognition rate of 92.80%.