Robust Recognition Based on Adaptive Combination of Weak Classifiers

Guoping Wang, Misha Pavel, Xubo Song

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We describe a novel adaptive method that achieves robustness in pattern classification by combining a large number of weak classifiers. The individual classifiers are trained on subsets of features of the training samples and the output classification is obtained by a weighted sum of the individual weak classifiers. When the classifier is applied to the test set, the combination weights are adaptively adjusted in accordance with the agreement among the individual classifiers. We evaluated the performances of several different combination methods using simulated data and the results proved to be robust.

Original languageEnglish (US)
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages2272-2276
Number of pages5
Volume3
StatePublished - 2003
EventInternational Joint Conference on Neural Networks 2003 - Portland, OR, United States
Duration: Jul 20 2003Jul 24 2003

Other

OtherInternational Joint Conference on Neural Networks 2003
CountryUnited States
CityPortland, OR
Period7/20/037/24/03

Fingerprint

Classifiers
Pattern recognition

ASJC Scopus subject areas

  • Software

Cite this

Wang, G., Pavel, M., & Song, X. (2003). Robust Recognition Based on Adaptive Combination of Weak Classifiers. In Proceedings of the International Joint Conference on Neural Networks (Vol. 3, pp. 2272-2276)

Robust Recognition Based on Adaptive Combination of Weak Classifiers. / Wang, Guoping; Pavel, Misha; Song, Xubo.

Proceedings of the International Joint Conference on Neural Networks. Vol. 3 2003. p. 2272-2276.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, G, Pavel, M & Song, X 2003, Robust Recognition Based on Adaptive Combination of Weak Classifiers. in Proceedings of the International Joint Conference on Neural Networks. vol. 3, pp. 2272-2276, International Joint Conference on Neural Networks 2003, Portland, OR, United States, 7/20/03.
Wang G, Pavel M, Song X. Robust Recognition Based on Adaptive Combination of Weak Classifiers. In Proceedings of the International Joint Conference on Neural Networks. Vol. 3. 2003. p. 2272-2276
Wang, Guoping ; Pavel, Misha ; Song, Xubo. / Robust Recognition Based on Adaptive Combination of Weak Classifiers. Proceedings of the International Joint Conference on Neural Networks. Vol. 3 2003. pp. 2272-2276
@inproceedings{2c5e8ae7c91e4d2e88e0d2d807d76b64,
title = "Robust Recognition Based on Adaptive Combination of Weak Classifiers",
abstract = "We describe a novel adaptive method that achieves robustness in pattern classification by combining a large number of weak classifiers. The individual classifiers are trained on subsets of features of the training samples and the output classification is obtained by a weighted sum of the individual weak classifiers. When the classifier is applied to the test set, the combination weights are adaptively adjusted in accordance with the agreement among the individual classifiers. We evaluated the performances of several different combination methods using simulated data and the results proved to be robust.",
author = "Guoping Wang and Misha Pavel and Xubo Song",
year = "2003",
language = "English (US)",
volume = "3",
pages = "2272--2276",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - Robust Recognition Based on Adaptive Combination of Weak Classifiers

AU - Wang, Guoping

AU - Pavel, Misha

AU - Song, Xubo

PY - 2003

Y1 - 2003

N2 - We describe a novel adaptive method that achieves robustness in pattern classification by combining a large number of weak classifiers. The individual classifiers are trained on subsets of features of the training samples and the output classification is obtained by a weighted sum of the individual weak classifiers. When the classifier is applied to the test set, the combination weights are adaptively adjusted in accordance with the agreement among the individual classifiers. We evaluated the performances of several different combination methods using simulated data and the results proved to be robust.

AB - We describe a novel adaptive method that achieves robustness in pattern classification by combining a large number of weak classifiers. The individual classifiers are trained on subsets of features of the training samples and the output classification is obtained by a weighted sum of the individual weak classifiers. When the classifier is applied to the test set, the combination weights are adaptively adjusted in accordance with the agreement among the individual classifiers. We evaluated the performances of several different combination methods using simulated data and the results proved to be robust.

UR - http://www.scopus.com/inward/record.url?scp=0141857564&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141857564&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0141857564

VL - 3

SP - 2272

EP - 2276

BT - Proceedings of the International Joint Conference on Neural Networks

ER -