AN UNSUPERVISED SONAR IMAGES SEGMENTATION APPROACH

Abdel-Ouahab Boudraa, Jean-Christophe Cexus

Abstract

In this work an unsupervised Sonar (Sound navigation and ranging) images segmentation is proposed. Due to the textural nature of the Sonar images, a band-pass filtering that takes into account the local spatial frequency of these images is proposed. Sonar image is passed through a bank of Gabor filters and the filtered images that possess a significant component of the original image are selected. To calculate the radial frequencies, a new approach is proposed. The selected filtered images are then subjected to a non-linear transformation. An energy measure is defined on the transformed images in order to compute texture features. The texture energy features are used as input to a clustering algorithm. The segmentation scheme has been successfully tested on real high-resolution Sonar images, yielding very promising results.

Download


Paper Citation


in Harvard Style

Boudraa A. and Cexus J. (2007). AN UNSUPERVISED SONAR IMAGES SEGMENTATION APPROACH . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, ISBN 978-972-8865-73-3, pages 165-170. DOI: 10.5220/0002056601650170


in Bibtex Style

@conference{visapp07,
author={Abdel-Ouahab Boudraa and Jean-Christophe Cexus},
title={AN UNSUPERVISED SONAR IMAGES SEGMENTATION APPROACH},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,},
year={2007},
pages={165-170},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002056601650170},
isbn={978-972-8865-73-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,
TI - AN UNSUPERVISED SONAR IMAGES SEGMENTATION APPROACH
SN - 978-972-8865-73-3
AU - Boudraa A.
AU - Cexus J.
PY - 2007
SP - 165
EP - 170
DO - 10.5220/0002056601650170