Self-Organizing Maps Approach to Object Localization in Sonar Imagery - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier
Conference Papers Year : 2003

Self-Organizing Maps Approach to Object Localization in Sonar Imagery

Abstract

The Self-Organizing Map is well-known as the unsupervised classification method. It is employed as classifier in various applications such as image segmentation. The main purpose of this paper is to identify and detect an object of interest on side scan sonar image. This work is performed by two steps. The first one is to split an image into regions of uniform texture using the Gray Level Co-occurrence Matrix Method (GLCM) which is widely used in texture segmentation application. The last one address the unsupervised learning method based on the Artificial Neural Networks (Self-Organizing Map or SOM) used for determining the comparative model of object of interest from an image. To increase the performance of SOM, we propose a penalty function based on data histogram visualization. After a brief review of both techniques (GLCM and SOM), we present our method and some results from several experiments on the real world data set.
Fichier principal
Vignette du fichier
D118.PDF (415.53 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

lirmm-00191933 , version 1 (26-11-2007)

Identifiers

  • HAL Id : lirmm-00191933 , version 1

Cite

Amornrit Puttipipatkajorn, Bruno Jouvencel. Self-Organizing Maps Approach to Object Localization in Sonar Imagery. ICAR 2003 - 11th International Conference on Advanced Robotics, 2003, Coimbra, Portugal. pp.1172-1177. ⟨lirmm-00191933⟩
135 View
376 Download

Share

More