A variational approach for color image segmentation

N Nasios; A G Bors

A variational approach for color image segmentation

Computer Science

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

Abstract

In this paper we use a variational Bayesian frame-work for color image segmentation. Each image is represented in the L*u*v color coordinate system before being segmented by the variational algorithm. The model chosen to describe the color images is a Gaussian mixture model. The parameter estimation uses variational learning by taking into account the uncertainty in parameter estimation. In the variational Bayesian approach we integrate over distributions of parameters. We propose a triaximum log-likelihood initialization approach for the Variational Expectation-Maximization (VEM) algorithm and we apply it to color image segmentation. The segmentation task in our approach consists of the estimation of the distribution hyperparameters.

Original language	English
Title of host publication	PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1
Editors	J Kittler, M Petrou, M Nixon
Place of Publication	LOS ALAMITOS
Publisher	IEEE Computer Society
Pages	680-683
Number of pages	4
ISBN (Print)	0-7695-2128-2
Publication status	Published - 2004
Event	17th International Conference on Pattern Recognition (ICPR) - Cambridge Duration: 23 Aug 2004 → 26 Aug 2004

Conference

Conference	17th International Conference on Pattern Recognition (ICPR)
City	Cambridge
Period	23/08/04 → 26/08/04

Keywords

ALGORITHM
MODELS

Cite this

@inproceedings{0cad995881b64e5fbd0398347406271f,

title = "A variational approach for color image segmentation",

abstract = "In this paper we use a variational Bayesian frame-work for color image segmentation. Each image is represented in the L*u*v color coordinate system before being segmented by the variational algorithm. The model chosen to describe the color images is a Gaussian mixture model. The parameter estimation uses variational learning by taking into account the uncertainty in parameter estimation. In the variational Bayesian approach we integrate over distributions of parameters. We propose a triaximum log-likelihood initialization approach for the Variational Expectation-Maximization (VEM) algorithm and we apply it to color image segmentation. The segmentation task in our approach consists of the estimation of the distribution hyperparameters.",

keywords = "ALGORITHM, MODELS",

author = "N Nasios and Bors, {A G}",

year = "2004",

language = "English",

isbn = "0-7695-2128-2",

pages = "680--683",

editor = "J Kittler and M Petrou and M Nixon",

booktitle = "PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1",

publisher = "IEEE Computer Society",

address = "United States",

note = "17th International Conference on Pattern Recognition (ICPR) ; Conference date: 23-08-2004 Through 26-08-2004",

}

TY - GEN

T1 - A variational approach for color image segmentation

AU - Nasios, N

AU - Bors, A G

PY - 2004

Y1 - 2004

N2 - In this paper we use a variational Bayesian frame-work for color image segmentation. Each image is represented in the L*u*v color coordinate system before being segmented by the variational algorithm. The model chosen to describe the color images is a Gaussian mixture model. The parameter estimation uses variational learning by taking into account the uncertainty in parameter estimation. In the variational Bayesian approach we integrate over distributions of parameters. We propose a triaximum log-likelihood initialization approach for the Variational Expectation-Maximization (VEM) algorithm and we apply it to color image segmentation. The segmentation task in our approach consists of the estimation of the distribution hyperparameters.

AB - In this paper we use a variational Bayesian frame-work for color image segmentation. Each image is represented in the L*u*v color coordinate system before being segmented by the variational algorithm. The model chosen to describe the color images is a Gaussian mixture model. The parameter estimation uses variational learning by taking into account the uncertainty in parameter estimation. In the variational Bayesian approach we integrate over distributions of parameters. We propose a triaximum log-likelihood initialization approach for the Variational Expectation-Maximization (VEM) algorithm and we apply it to color image segmentation. The segmentation task in our approach consists of the estimation of the distribution hyperparameters.

KW - ALGORITHM

KW - MODELS

M3 - Conference contribution

SN - 0-7695-2128-2

SP - 680

EP - 683

BT - PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1

A2 - Kittler, J

A2 - Petrou, M

A2 - Nixon, M

PB - IEEE Computer Society

CY - LOS ALAMITOS

T2 - 17th International Conference on Pattern Recognition (ICPR)

Y2 - 23 August 2004 through 26 August 2004

ER -