Handwritten character recognition based on hybrid neural networks

Peng Wang; Guangmin Sun; Xinming Zhang

doi:10.1117/12.441669

Handwritten character recognition based on hybrid neural networks

Peng Wang, Guangmin Sun, Xinming Zhang

Research output: Contribution to journal › Conference article › peer-review

2 Scopus citations

Abstract

A hybrid neural network system for the recognition of handwritten character using SOFM,BP and Fuzzy network is presented. The horizontal and vertical project of preprocessed character and 4_directional edge project are used as feature vectors. In order to improve the recognition effect, the GAT algorithm is applied. Through the hybrid neural network system, the recognition rate is improved visibly.

Original language	English
Pages (from-to)	65-70
Number of pages	6
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	4555
DOIs	https://doi.org/10.1117/12.441669
State	Published - 2001
Externally published	Yes
Event	Neural Network and Distributed Processing - Wuhan, China Duration: 22 Oct 2001 → 23 Oct 2001

Keywords

Character recognition
Neural network

Access to Document

10.1117/12.441669

Cite this

@article{ae37732aa90f4566bea90a6fdbc014ac,

title = "Handwritten character recognition based on hybrid neural networks",

abstract = "A hybrid neural network system for the recognition of handwritten character using SOFM,BP and Fuzzy network is presented. The horizontal and vertical project of preprocessed character and 4\_directional edge project are used as feature vectors. In order to improve the recognition effect, the GAT algorithm is applied. Through the hybrid neural network system, the recognition rate is improved visibly.",

keywords = "Character recognition, Neural network",

author = "Peng Wang and Guangmin Sun and Xinming Zhang",

year = "2001",

doi = "10.1117/12.441669",

language = "English",

volume = "4555",

pages = "65--70",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Neural Network and Distributed Processing ; Conference date: 22-10-2001 Through 23-10-2001",

}

TY - JOUR

T1 - Handwritten character recognition based on hybrid neural networks

AU - Wang, Peng

AU - Sun, Guangmin

AU - Zhang, Xinming

PY - 2001

Y1 - 2001

N2 - A hybrid neural network system for the recognition of handwritten character using SOFM,BP and Fuzzy network is presented. The horizontal and vertical project of preprocessed character and 4_directional edge project are used as feature vectors. In order to improve the recognition effect, the GAT algorithm is applied. Through the hybrid neural network system, the recognition rate is improved visibly.

AB - A hybrid neural network system for the recognition of handwritten character using SOFM,BP and Fuzzy network is presented. The horizontal and vertical project of preprocessed character and 4_directional edge project are used as feature vectors. In order to improve the recognition effect, the GAT algorithm is applied. Through the hybrid neural network system, the recognition rate is improved visibly.

KW - Character recognition

KW - Neural network

UR - https://www.scopus.com/pages/publications/0035768036

U2 - 10.1117/12.441669

DO - 10.1117/12.441669

M3 - Conference article

AN - SCOPUS:0035768036

SN - 0277-786X

VL - 4555

SP - 65

EP - 70

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Neural Network and Distributed Processing

Y2 - 22 October 2001 through 23 October 2001

ER -

Handwritten character recognition based on hybrid neural networks

Abstract

Keywords

Access to Document

Fingerprint

Cite this