Feature selection by genetic algorithm that adopts the principle of margin-maximization and its application to character recognition

Akira Suzuki, Satoshi Shimada, Yoshimasa Kimura, Shunichi Yonemura, Masashi Morimoto

研究成果: Article

抄録

This paper proposes a feature selection method that improves the recognition rate significantly for not only training samples but also unknown samples by using the principle of margin-maximization in the support vector machine (SVM). SVM is well-known as a recognition method that can discriminate unknown samples with high precision, so feature selection with high recognition rates for unknown samples can be expected by adopting the principle of margin-maximization, the technical basis of SVM. We perform experiments on five sets of hand-written Kanji character patterns. Each set consists of patterns in two similar categories. The results show that the proposed method improves the recognition rate significantly for not only training samples but also the unknown samples as expected.

元の言語English
ページ(範囲)131-139
ページ数9
ジャーナルJournal of the Institute of Image Electronics Engineers of Japan
41
発行部数2
出版物ステータスPublished - 2012
外部発表Yes

Fingerprint

Character recognition
Support vector machines
Feature extraction
Genetic algorithms
Experiments

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Electrical and Electronic Engineering

これを引用

@article{9a69e53ce03e405cbea41cb246d233a1,
title = "Feature selection by genetic algorithm that adopts the principle of margin-maximization and its application to character recognition",
abstract = "This paper proposes a feature selection method that improves the recognition rate significantly for not only training samples but also unknown samples by using the principle of margin-maximization in the support vector machine (SVM). SVM is well-known as a recognition method that can discriminate unknown samples with high precision, so feature selection with high recognition rates for unknown samples can be expected by adopting the principle of margin-maximization, the technical basis of SVM. We perform experiments on five sets of hand-written Kanji character patterns. Each set consists of patterns in two similar categories. The results show that the proposed method improves the recognition rate significantly for not only training samples but also the unknown samples as expected.",
keywords = "Character recognition, Feature selection, Genetic algorithms, Margin maximization, Support vector machine",
author = "Akira Suzuki and Satoshi Shimada and Yoshimasa Kimura and Shunichi Yonemura and Masashi Morimoto",
year = "2012",
language = "English",
volume = "41",
pages = "131--139",
journal = "Journal of the Institute of Image Electronics Engineers of Japan",
issn = "0285-9831",
publisher = "Institute of Image Electronics Engineers of Japan",
number = "2",

}

TY - JOUR

T1 - Feature selection by genetic algorithm that adopts the principle of margin-maximization and its application to character recognition

AU - Suzuki, Akira

AU - Shimada, Satoshi

AU - Kimura, Yoshimasa

AU - Yonemura, Shunichi

AU - Morimoto, Masashi

PY - 2012

Y1 - 2012

N2 - This paper proposes a feature selection method that improves the recognition rate significantly for not only training samples but also unknown samples by using the principle of margin-maximization in the support vector machine (SVM). SVM is well-known as a recognition method that can discriminate unknown samples with high precision, so feature selection with high recognition rates for unknown samples can be expected by adopting the principle of margin-maximization, the technical basis of SVM. We perform experiments on five sets of hand-written Kanji character patterns. Each set consists of patterns in two similar categories. The results show that the proposed method improves the recognition rate significantly for not only training samples but also the unknown samples as expected.

AB - This paper proposes a feature selection method that improves the recognition rate significantly for not only training samples but also unknown samples by using the principle of margin-maximization in the support vector machine (SVM). SVM is well-known as a recognition method that can discriminate unknown samples with high precision, so feature selection with high recognition rates for unknown samples can be expected by adopting the principle of margin-maximization, the technical basis of SVM. We perform experiments on five sets of hand-written Kanji character patterns. Each set consists of patterns in two similar categories. The results show that the proposed method improves the recognition rate significantly for not only training samples but also the unknown samples as expected.

KW - Character recognition

KW - Feature selection

KW - Genetic algorithms

KW - Margin maximization

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84902143516&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902143516&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84902143516

VL - 41

SP - 131

EP - 139

JO - Journal of the Institute of Image Electronics Engineers of Japan

JF - Journal of the Institute of Image Electronics Engineers of Japan

SN - 0285-9831

IS - 2

ER -