Analytical decision boundary feature extraction for neural networks for the recognition of unconstrained handwritten digits

Jinwook Go; Chulhee Lee

Analytical decision boundary feature extraction for neural networks for the recognition of unconstrained handwritten digits

Jinwook Go, Chulhee Lee

Department of Electrical and Electronic Engineering

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

3 Citations (Scopus)

Abstract

Although neural networks have been successfully applied for the recognition of unconstrained handwritten characters, there have been few efficient feature extraction algorithms, resulting in inefficient neural networks. In this paper, we apply a recently published decision boundary feature extraction algorithm to neural networks for the recognition of handwritten digits and reduce the computational cost and complexity of neural networks. Experiments show that the proposed feature extraction algorithm can reduce the number of features significantly without sacrificing the performance.

Original language	English
Pages (from-to)	2731-2734
Number of pages	4
Journal	Proceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume	4
Publication status	Published - 2000
Event	2000 IEEE International Conference on Systems, Man and Cybernetics - Nashville, TN, USA Duration: 2000 Oct 8 → 2000 Oct 11

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Hardware and Architecture

Cite this

@article{9e9c4de707db4cb4bda4d81a24b48998,

title = "Analytical decision boundary feature extraction for neural networks for the recognition of unconstrained handwritten digits",

abstract = "Although neural networks have been successfully applied for the recognition of unconstrained handwritten characters, there have been few efficient feature extraction algorithms, resulting in inefficient neural networks. In this paper, we apply a recently published decision boundary feature extraction algorithm to neural networks for the recognition of handwritten digits and reduce the computational cost and complexity of neural networks. Experiments show that the proposed feature extraction algorithm can reduce the number of features significantly without sacrificing the performance.",

author = "Jinwook Go and Chulhee Lee",

year = "2000",

language = "English",

volume = "4",

pages = "2731--2734",

journal = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",

issn = "0884-3627",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2000 IEEE International Conference on Systems, Man and Cybernetics ; Conference date: 08-10-2000 Through 11-10-2000",

}

TY - JOUR

T1 - Analytical decision boundary feature extraction for neural networks for the recognition of unconstrained handwritten digits

AU - Go, Jinwook

AU - Lee, Chulhee

PY - 2000

Y1 - 2000

N2 - Although neural networks have been successfully applied for the recognition of unconstrained handwritten characters, there have been few efficient feature extraction algorithms, resulting in inefficient neural networks. In this paper, we apply a recently published decision boundary feature extraction algorithm to neural networks for the recognition of handwritten digits and reduce the computational cost and complexity of neural networks. Experiments show that the proposed feature extraction algorithm can reduce the number of features significantly without sacrificing the performance.

AB - Although neural networks have been successfully applied for the recognition of unconstrained handwritten characters, there have been few efficient feature extraction algorithms, resulting in inefficient neural networks. In this paper, we apply a recently published decision boundary feature extraction algorithm to neural networks for the recognition of handwritten digits and reduce the computational cost and complexity of neural networks. Experiments show that the proposed feature extraction algorithm can reduce the number of features significantly without sacrificing the performance.

UR - http://www.scopus.com/inward/record.url?scp=0034506491&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034506491&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0034506491

SN - 0884-3627

VL - 4

SP - 2731

EP - 2734

JO - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

JF - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

T2 - 2000 IEEE International Conference on Systems, Man and Cybernetics

Y2 - 8 October 2000 through 11 October 2000

ER -

Analytical decision boundary feature extraction for neural networks for the recognition of unconstrained handwritten digits

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this