Feature Transformation with Generalized Learning Vector Quantization for Hand-Written Chinese Character Recognition

Mu-King TSAY; Keh-Hwa SHYU; Pao-Chung CHANG

Feature Transformation with Generalized Learning Vector Quantization for Hand-Written Chinese Character Recognition

Mu-King TSAY, Keh-Hwa SHYU, Pao-Chung CHANG

Full Text Views

0

Cite this

Summary :

In this paper, the generalized learning vector quantization (GLVQ) algorithm is applied to design a hand-written Chinese character recognition system. The system proposed herein consists of two modules, feature transformation and recognizer. The feature transformation module is designed to extract discriminative features to enhance the recognition performance. The initial feature transformation matrix is obtained by using Fisher's linear discriminant (FLD) function. A template matching with minimum distance criterion recognizer is used and each character is represented by one reference template. These reference templates and the elements of the feature transformation matrix are trained by using the generalized learning vector quantization algorithm. In the experiments, 540100 (5401 100) hand-written Chinese character samples are used to build the recognition system and the other 540100 (5401 100) samples are used to do the open test. A good performance of 92.18 % accuracy is achieved by proposed system.

Publication: IEICE TRANSACTIONS on Information Vol.E82-D No.3 pp.687-692

Publication Date: 1999/03/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Image Processing,Computer Graphics and Pattern Recognition

Cite this

Copy

Mu-King TSAY, Keh-Hwa SHYU, Pao-Chung CHANG, "Feature Transformation with Generalized Learning Vector Quantization for Hand-Written Chinese Character Recognition" in IEICE TRANSACTIONS on Information, vol. E82-D, no. 3, pp. 687-692, March 1999, doi: .
Abstract: In this paper, the generalized learning vector quantization (GLVQ) algorithm is applied to design a hand-written Chinese character recognition system. The system proposed herein consists of two modules, feature transformation and recognizer. The feature transformation module is designed to extract discriminative features to enhance the recognition performance. The initial feature transformation matrix is obtained by using Fisher's linear discriminant (FLD) function. A template matching with minimum distance criterion recognizer is used and each character is represented by one reference template. These reference templates and the elements of the feature transformation matrix are trained by using the generalized learning vector quantization algorithm. In the experiments, 540100 (5401 100) hand-written Chinese character samples are used to build the recognition system and the other 540100 (5401 100) samples are used to do the open test. A good performance of 92.18 % accuracy is achieved by proposed system.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_3_687/_p

Copy

@ARTICLE{e82-d_3_687,
author={Mu-King TSAY, Keh-Hwa SHYU, Pao-Chung CHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Feature Transformation with Generalized Learning Vector Quantization for Hand-Written Chinese Character Recognition},
year={1999},
volume={E82-D},
number={3},
pages={687-692},
abstract={In this paper, the generalized learning vector quantization (GLVQ) algorithm is applied to design a hand-written Chinese character recognition system. The system proposed herein consists of two modules, feature transformation and recognizer. The feature transformation module is designed to extract discriminative features to enhance the recognition performance. The initial feature transformation matrix is obtained by using Fisher's linear discriminant (FLD) function. A template matching with minimum distance criterion recognizer is used and each character is represented by one reference template. These reference templates and the elements of the feature transformation matrix are trained by using the generalized learning vector quantization algorithm. In the experiments, 540100 (5401 100) hand-written Chinese character samples are used to build the recognition system and the other 540100 (5401 100) samples are used to do the open test. A good performance of 92.18 % accuracy is achieved by proposed system.},
keywords={},
doi={},
ISSN={},
month={March},}

Copy

TY - JOUR
TI - Feature Transformation with Generalized Learning Vector Quantization for Hand-Written Chinese Character Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 687
EP - 692
AU - Mu-King TSAY
AU - Keh-Hwa SHYU
AU - Pao-Chung CHANG
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 1999
AB - In this paper, the generalized learning vector quantization (GLVQ) algorithm is applied to design a hand-written Chinese character recognition system. The system proposed herein consists of two modules, feature transformation and recognizer. The feature transformation module is designed to extract discriminative features to enhance the recognition performance. The initial feature transformation matrix is obtained by using Fisher's linear discriminant (FLD) function. A template matching with minimum distance criterion recognizer is used and each character is represented by one reference template. These reference templates and the elements of the feature transformation matrix are trained by using the generalized learning vector quantization algorithm. In the experiments, 540100 (5401 100) hand-written Chinese character samples are used to build the recognition system and the other 540100 (5401 100) samples are used to do the open test. A good performance of 92.18 % accuracy is achieved by proposed system.
ER -