Boosting mixtures of Gaussians under normalized linear transformations for image classification

Ahmed Fawzi Otoom; Oscar Perez Concha; Massimo Piccardi

Boosting mixtures of Gaussians under normalized linear transformations for image classification

Ahmed Fawzi Otoom^*, Oscar Perez Concha, Massimo Piccardi

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

We address the problem of image classification. Our aim is to improve the performance of MLiT: mixture of Gaussians under Linear transformations, a feature-based classifier proposed in [1] aiming to reduce dimensionality based on a linear transformation which is not restricted to be orthogonal. Boosting might offer an interesting solution by improving the performance of a given base classification algorithm. In this paper, we propose to integrate MLiT within the framework of AdaBoost, which is a widely applied method for boosting. For experimental validation, we have evaluated the proposed method on the four UCI data sets (Vehicle, OpticDigit, WDBC, WPBC) [2] and the author's own. Boosting has proved capable of enhancing the performance of the base classifier on two data sets with improvements of up to 12.8%.

Original language	English
Title of host publication	ICITA 2011
Subtitle of host publication	7th International Conference on Information Technology and Application
Place of Publication	New York
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	184-189
Number of pages	6
ISBN (Print)	9780980326741
Publication status	Published - 2011
Externally published	Yes
Event	7th International Conference on Information Technology and Application, ICITA 2011 - Sydney, NSW, Australia Duration: 21 Nov 2011 → 24 Nov 2011

Other

Other	7th International Conference on Information Technology and Application, ICITA 2011
Country/Territory	Australia
City	Sydney, NSW
Period	21/11/11 → 24/11/11

Keywords

AdaBoost
Dimensionality reduction
Image classification
Linear transformation

Cite this

@inproceedings{4effe6dee5974d639ecf7433fddc9a93,

title = "Boosting mixtures of Gaussians under normalized linear transformations for image classification",

abstract = "We address the problem of image classification. Our aim is to improve the performance of MLiT: mixture of Gaussians under Linear transformations, a feature-based classifier proposed in [1] aiming to reduce dimensionality based on a linear transformation which is not restricted to be orthogonal. Boosting might offer an interesting solution by improving the performance of a given base classification algorithm. In this paper, we propose to integrate MLiT within the framework of AdaBoost, which is a widely applied method for boosting. For experimental validation, we have evaluated the proposed method on the four UCI data sets (Vehicle, OpticDigit, WDBC, WPBC) [2] and the author's own. Boosting has proved capable of enhancing the performance of the base classifier on two data sets with improvements of up to 12.8%.",

keywords = "AdaBoost, Dimensionality reduction, Image classification, Linear transformation",

author = "Otoom, {Ahmed Fawzi} and Concha, {Oscar Perez} and Massimo Piccardi",

year = "2011",

language = "English",

isbn = "9780980326741",

pages = "184--189",

booktitle = "ICITA 2011",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "7th International Conference on Information Technology and Application, ICITA 2011 ; Conference date: 21-11-2011 Through 24-11-2011",

}

Otoom, AF, Concha, OP & Piccardi, M 2011, Boosting mixtures of Gaussians under normalized linear transformations for image classification. in ICITA 2011: 7th International Conference on Information Technology and Application. Institute of Electrical and Electronics Engineers (IEEE), New York, pp. 184-189, 7th International Conference on Information Technology and Application, ICITA 2011, Sydney, NSW, Australia, 21/11/11.

Boosting mixtures of Gaussians under normalized linear transformations for image classification. / Otoom, Ahmed Fawzi; Concha, Oscar Perez; Piccardi, Massimo.
ICITA 2011: 7th International Conference on Information Technology and Application. New York: Institute of Electrical and Electronics Engineers (IEEE), 2011. p. 184-189.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Boosting mixtures of Gaussians under normalized linear transformations for image classification

AU - Otoom, Ahmed Fawzi

AU - Concha, Oscar Perez

AU - Piccardi, Massimo

PY - 2011

Y1 - 2011

N2 - We address the problem of image classification. Our aim is to improve the performance of MLiT: mixture of Gaussians under Linear transformations, a feature-based classifier proposed in [1] aiming to reduce dimensionality based on a linear transformation which is not restricted to be orthogonal. Boosting might offer an interesting solution by improving the performance of a given base classification algorithm. In this paper, we propose to integrate MLiT within the framework of AdaBoost, which is a widely applied method for boosting. For experimental validation, we have evaluated the proposed method on the four UCI data sets (Vehicle, OpticDigit, WDBC, WPBC) [2] and the author's own. Boosting has proved capable of enhancing the performance of the base classifier on two data sets with improvements of up to 12.8%.

AB - We address the problem of image classification. Our aim is to improve the performance of MLiT: mixture of Gaussians under Linear transformations, a feature-based classifier proposed in [1] aiming to reduce dimensionality based on a linear transformation which is not restricted to be orthogonal. Boosting might offer an interesting solution by improving the performance of a given base classification algorithm. In this paper, we propose to integrate MLiT within the framework of AdaBoost, which is a widely applied method for boosting. For experimental validation, we have evaluated the proposed method on the four UCI data sets (Vehicle, OpticDigit, WDBC, WPBC) [2] and the author's own. Boosting has proved capable of enhancing the performance of the base classifier on two data sets with improvements of up to 12.8%.

KW - AdaBoost

KW - Dimensionality reduction

KW - Image classification

KW - Linear transformation

UR - http://www.scopus.com/inward/record.url?scp=84868105821&partnerID=8YFLogxK

M3 - Conference proceeding contribution

AN - SCOPUS:84868105821

SN - 9780980326741

SP - 184

EP - 189

BT - ICITA 2011

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - New York

T2 - 7th International Conference on Information Technology and Application, ICITA 2011

Y2 - 21 November 2011 through 24 November 2011

ER -

Boosting mixtures of Gaussians under normalized linear transformations for image classification

Abstract

Other

Keywords

Other files and links

Fingerprint

Cite this