Segmentation of On-Line Freely Written Japanese Text Using SVM for Improving Text Recognition

Bilan ZHU; Masaki NAKAGAWA

doi:10.1093/ietisy/e91-d.1.105

Segmentation of On-Line Freely Written Japanese Text Using SVM for Improving Text Recognition

Bilan ZHU, Masaki NAKAGAWA

Full Text Views

0

Cite this

Summary :

This paper describes a method of producing segmentation point candidates for on-line handwritten Japanese text by a support vector machine (SVM) to improve text recognition. This method extracts multi-dimensional features from on-line strokes of handwritten text and applies the SVM to the extracted features to produces segmentation point candidates. We incorporate the method into the segmentation by recognition scheme based on a stochastic model which evaluates the likelihood composed of character pattern structure, character segmentation, character recognition and context to finally determine segmentation points and recognize handwritten Japanese text. This paper also shows the details of generating segmentation point candidates in order to achieve high discrimination rate by finding the optimal combination of the segmentation threshold and the concatenation threshold. We compare the method for segmentation by the SVM with that by a neural network (NN) using the database HANDS-Kondate_t_bf-2001-11 and show the result that the method by the SVM bring about a better segmentation rate and character recognition rate.

Publication: IEICE TRANSACTIONS on Information Vol.E91-D No.1 pp.105-113

Publication Date: 2008/01/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e91-d.1.105

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Cite this

Copy

Bilan ZHU, Masaki NAKAGAWA, "Segmentation of On-Line Freely Written Japanese Text Using SVM for Improving Text Recognition" in IEICE TRANSACTIONS on Information, vol. E91-D, no. 1, pp. 105-113, January 2008, doi: 10.1093/ietisy/e91-d.1.105.
Abstract: This paper describes a method of producing segmentation point candidates for on-line handwritten Japanese text by a support vector machine (SVM) to improve text recognition. This method extracts multi-dimensional features from on-line strokes of handwritten text and applies the SVM to the extracted features to produces segmentation point candidates. We incorporate the method into the segmentation by recognition scheme based on a stochastic model which evaluates the likelihood composed of character pattern structure, character segmentation, character recognition and context to finally determine segmentation points and recognize handwritten Japanese text. This paper also shows the details of generating segmentation point candidates in order to achieve high discrimination rate by finding the optimal combination of the segmentation threshold and the concatenation threshold. We compare the method for segmentation by the SVM with that by a neural network (NN) using the database HANDS-Kondate_t_bf-2001-11 and show the result that the method by the SVM bring about a better segmentation rate and character recognition rate.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.1.105/_p

Copy

@ARTICLE{e91-d_1_105,
author={Bilan ZHU, Masaki NAKAGAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Segmentation of On-Line Freely Written Japanese Text Using SVM for Improving Text Recognition},
year={2008},
volume={E91-D},
number={1},
pages={105-113},
abstract={This paper describes a method of producing segmentation point candidates for on-line handwritten Japanese text by a support vector machine (SVM) to improve text recognition. This method extracts multi-dimensional features from on-line strokes of handwritten text and applies the SVM to the extracted features to produces segmentation point candidates. We incorporate the method into the segmentation by recognition scheme based on a stochastic model which evaluates the likelihood composed of character pattern structure, character segmentation, character recognition and context to finally determine segmentation points and recognize handwritten Japanese text. This paper also shows the details of generating segmentation point candidates in order to achieve high discrimination rate by finding the optimal combination of the segmentation threshold and the concatenation threshold. We compare the method for segmentation by the SVM with that by a neural network (NN) using the database HANDS-Kondate_t_bf-2001-11 and show the result that the method by the SVM bring about a better segmentation rate and character recognition rate.},
keywords={},
doi={10.1093/ietisy/e91-d.1.105},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - Segmentation of On-Line Freely Written Japanese Text Using SVM for Improving Text Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 105
EP - 113
AU - Bilan ZHU
AU - Masaki NAKAGAWA
PY - 2008
DO - 10.1093/ietisy/e91-d.1.105
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2008
AB - This paper describes a method of producing segmentation point candidates for on-line handwritten Japanese text by a support vector machine (SVM) to improve text recognition. This method extracts multi-dimensional features from on-line strokes of handwritten text and applies the SVM to the extracted features to produces segmentation point candidates. We incorporate the method into the segmentation by recognition scheme based on a stochastic model which evaluates the likelihood composed of character pattern structure, character segmentation, character recognition and context to finally determine segmentation points and recognize handwritten Japanese text. This paper also shows the details of generating segmentation point candidates in order to achieve high discrimination rate by finding the optimal combination of the segmentation threshold and the concatenation threshold. We compare the method for segmentation by the SVM with that by a neural network (NN) using the database HANDS-Kondate_t_bf-2001-11 and show the result that the method by the SVM bring about a better segmentation rate and character recognition rate.
ER -