Integrating Statistical and Structural Approaches to Handprinted Chinese Character Recognition

Wen-Chung KAO; Tai-Ming PARNG

Integrating Statistical and Structural Approaches to Handprinted Chinese Character Recognition

Wen-Chung KAO, Tai-Ming PARNG

Full Text Views

0

Cite this

Summary :

Handprinted Chinese character recognition (HCCR) can be classified into two major approaches: statistical and structural. While neither of these two approaches can lead to a total and practical solution for HCCR, integrating them to take advantages of both seems to be a promising and obviously feasible approach. But, how to integrate them would be a big issue. In this paper, we propose an integrated HCCR system. The system starts from a statistical phase. This phase uses line-density-distribution-based features extracted after nonlinear normalization to guarantee that different writing variations of the same character have similar feature vectors. It removes accurately and efficiently the impossible candidates and results in a final candidate set. Then follows the structural phase, which inherits the line segments used in the statistical phase and extracts a set of stroke substructures as features. These features are used to discriminate the similar characters in the final candidate set and hence improve the recognition rate. Tested by using a large set of characters in a handprinted Chinese character database, the proposed HCCR system is robust and can achieve 96 percent accuracy for characters in the first 100 variations of the database.

Publication: IEICE TRANSACTIONS on Information Vol.E81-D No.4 pp.391-400

Publication Date: 1998/04/25

Publicized

Online ISSN

DOI

Type of Manuscript

Category: Image Processing,Computer Graphics and Pattern Recognition

Cite this

Copy

Wen-Chung KAO, Tai-Ming PARNG, "Integrating Statistical and Structural Approaches to Handprinted Chinese Character Recognition" in IEICE TRANSACTIONS on Information, vol. E81-D, no. 4, pp. 391-400, April 1998, doi: .
Abstract: Handprinted Chinese character recognition (HCCR) can be classified into two major approaches: statistical and structural. While neither of these two approaches can lead to a total and practical solution for HCCR, integrating them to take advantages of both seems to be a promising and obviously feasible approach. But, how to integrate them would be a big issue. In this paper, we propose an integrated HCCR system. The system starts from a statistical phase. This phase uses line-density-distribution-based features extracted after nonlinear normalization to guarantee that different writing variations of the same character have similar feature vectors. It removes accurately and efficiently the impossible candidates and results in a final candidate set. Then follows the structural phase, which inherits the line segments used in the statistical phase and extracts a set of stroke substructures as features. These features are used to discriminate the similar characters in the final candidate set and hence improve the recognition rate. Tested by using a large set of characters in a handprinted Chinese character database, the proposed HCCR system is robust and can achieve 96 percent accuracy for characters in the first 100 variations of the database.
URL: https://global.ieice.org/en_transactions/information/10.1587/e81-d_4_391/_p

Copy

@ARTICLE{e81-d_4_391,
author={Wen-Chung KAO, Tai-Ming PARNG, },
journal={IEICE TRANSACTIONS on Information},
title={Integrating Statistical and Structural Approaches to Handprinted Chinese Character Recognition},
year={1998},
volume={E81-D},
number={4},
pages={391-400},
abstract={Handprinted Chinese character recognition (HCCR) can be classified into two major approaches: statistical and structural. While neither of these two approaches can lead to a total and practical solution for HCCR, integrating them to take advantages of both seems to be a promising and obviously feasible approach. But, how to integrate them would be a big issue. In this paper, we propose an integrated HCCR system. The system starts from a statistical phase. This phase uses line-density-distribution-based features extracted after nonlinear normalization to guarantee that different writing variations of the same character have similar feature vectors. It removes accurately and efficiently the impossible candidates and results in a final candidate set. Then follows the structural phase, which inherits the line segments used in the statistical phase and extracts a set of stroke substructures as features. These features are used to discriminate the similar characters in the final candidate set and hence improve the recognition rate. Tested by using a large set of characters in a handprinted Chinese character database, the proposed HCCR system is robust and can achieve 96 percent accuracy for characters in the first 100 variations of the database.},
keywords={},
doi={},
ISSN={},
month={April},}

Copy

TY - JOUR
TI - Integrating Statistical and Structural Approaches to Handprinted Chinese Character Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 391
EP - 400
AU - Wen-Chung KAO
AU - Tai-Ming PARNG
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E81-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 1998
AB - Handprinted Chinese character recognition (HCCR) can be classified into two major approaches: statistical and structural. While neither of these two approaches can lead to a total and practical solution for HCCR, integrating them to take advantages of both seems to be a promising and obviously feasible approach. But, how to integrate them would be a big issue. In this paper, we propose an integrated HCCR system. The system starts from a statistical phase. This phase uses line-density-distribution-based features extracted after nonlinear normalization to guarantee that different writing variations of the same character have similar feature vectors. It removes accurately and efficiently the impossible candidates and results in a final candidate set. Then follows the structural phase, which inherits the line segments used in the statistical phase and extracts a set of stroke substructures as features. These features are used to discriminate the similar characters in the final candidate set and hence improve the recognition rate. Tested by using a large set of characters in a handprinted Chinese character database, the proposed HCCR system is robust and can achieve 96 percent accuracy for characters in the first 100 variations of the database.
ER -