Optimizing feature extraction for multiclass problems

Chul Hee Lee, Euisun Choi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Feature extraction has been an important topic in pattern classification and studied extensively by many authors. Most conventional feature extraction methods are performed using a criterion function between two classes or a global function. Although these methods work relatively well in most cases, generally it is not optimal in any sense for multiclass problems. In this paper, we propose a method optimizing feature extraction for multiclass problems. We first investigated the distribution of the classification accuracy of multiclass problems in the feature space and found that there exist much better feature sets that conventional feature extraction algorithms fail to find. Then we propose an algorithm that finds such features. Experiments show that the proposed algorithm consistently provides a superior performance compared with the conventional feature extraction algorithms.

Original languageEnglish
Pages (from-to)402-405
Number of pages4
JournalProceedings - International Conference on Pattern Recognition
Volume15
Issue number2
Publication statusPublished - 2000 Dec 1

Fingerprint

Feature extraction
Pattern recognition
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

@article{0506b836b4a544f28c61b3088361f22e,
title = "Optimizing feature extraction for multiclass problems",
abstract = "Feature extraction has been an important topic in pattern classification and studied extensively by many authors. Most conventional feature extraction methods are performed using a criterion function between two classes or a global function. Although these methods work relatively well in most cases, generally it is not optimal in any sense for multiclass problems. In this paper, we propose a method optimizing feature extraction for multiclass problems. We first investigated the distribution of the classification accuracy of multiclass problems in the feature space and found that there exist much better feature sets that conventional feature extraction algorithms fail to find. Then we propose an algorithm that finds such features. Experiments show that the proposed algorithm consistently provides a superior performance compared with the conventional feature extraction algorithms.",
author = "Lee, {Chul Hee} and Euisun Choi",
year = "2000",
month = "12",
day = "1",
language = "English",
volume = "15",
pages = "402--405",
journal = "Proceedings - International Conference on Pattern Recognition",
issn = "1051-4651",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Optimizing feature extraction for multiclass problems. / Lee, Chul Hee; Choi, Euisun.

In: Proceedings - International Conference on Pattern Recognition, Vol. 15, No. 2, 01.12.2000, p. 402-405.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Optimizing feature extraction for multiclass problems

AU - Lee, Chul Hee

AU - Choi, Euisun

PY - 2000/12/1

Y1 - 2000/12/1

N2 - Feature extraction has been an important topic in pattern classification and studied extensively by many authors. Most conventional feature extraction methods are performed using a criterion function between two classes or a global function. Although these methods work relatively well in most cases, generally it is not optimal in any sense for multiclass problems. In this paper, we propose a method optimizing feature extraction for multiclass problems. We first investigated the distribution of the classification accuracy of multiclass problems in the feature space and found that there exist much better feature sets that conventional feature extraction algorithms fail to find. Then we propose an algorithm that finds such features. Experiments show that the proposed algorithm consistently provides a superior performance compared with the conventional feature extraction algorithms.

AB - Feature extraction has been an important topic in pattern classification and studied extensively by many authors. Most conventional feature extraction methods are performed using a criterion function between two classes or a global function. Although these methods work relatively well in most cases, generally it is not optimal in any sense for multiclass problems. In this paper, we propose a method optimizing feature extraction for multiclass problems. We first investigated the distribution of the classification accuracy of multiclass problems in the feature space and found that there exist much better feature sets that conventional feature extraction algorithms fail to find. Then we propose an algorithm that finds such features. Experiments show that the proposed algorithm consistently provides a superior performance compared with the conventional feature extraction algorithms.

UR - http://www.scopus.com/inward/record.url?scp=34147177311&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34147177311&partnerID=8YFLogxK

M3 - Article

VL - 15

SP - 402

EP - 405

JO - Proceedings - International Conference on Pattern Recognition

JF - Proceedings - International Conference on Pattern Recognition

SN - 1051-4651

IS - 2

ER -