Targets Classification on Multispectral Images using Connectionists Methods
American Journal of Physics and Applications
Volume 3, Issue 3, May 2015, Pages: 86-91
Received: Apr. 4, 2015; Accepted: Apr. 17, 2015; Published: Apr. 27, 2015
Views 3416      Downloads 308
Authors
Samir Zeriouh, Information Optronic Treatment Team, Atomic, Mechanical, Photonic and Energy Laboratory, Faculty of Science, Moulay Ismail University, Zitoune, Meknès, Morocco
Mustapha Boutahri, Information Optronic Treatment Team, Atomic, Mechanical, Photonic and Energy Laboratory, Faculty of Science, Moulay Ismail University, Zitoune, Meknès, Morocco
Said El Yamani, Information Optronic Treatment Team, Atomic, Mechanical, Photonic and Energy Laboratory, Faculty of Science, Moulay Ismail University, Zitoune, Meknès, Morocco
Ahmed Roukhe, Information Optronic Treatment Team, Atomic, Mechanical, Photonic and Energy Laboratory, Faculty of Science, Moulay Ismail University, Zitoune, Meknès, Morocco
Article Tools
Follow on us
Abstract
Identification of targets on remote sensing images depends mainly on the databases representing different classes. In this context, this paper proposes a connectionist system using a two-dimensional Kohonen self-organizing map to build a database of some identified targets on a multi-band satellite image. After an enhancing process, essentially based on a non-linear filtering, the system performs a non-supervised classification of a reference image in order to extract the sequence of samples of the reflectance coefficients related to the desired targets. This classification will be used later for automatic extraction of these targets on other stages.
Keywords
Multispectral Image, Classification, Identification, Artificial Neural Networks, Self-Organizing Map
To cite this article
Samir Zeriouh, Mustapha Boutahri, Said El Yamani, Ahmed Roukhe, Targets Classification on Multispectral Images using Connectionists Methods, American Journal of Physics and Applications. Vol. 3, No. 3, 2015, pp. 86-91. doi: 10.11648/j.ajpa.20150303.14
References
[1]
Mukesh C. Motwani, Mukesh C. Gadiya, Rakhi C. Motwani, Frederick C. Harris, Jr, “Survey of Image Denoising Techniques,” Proc. of GSPx 2004, Santa Clara Convention Center, Santa Clara, CA, 2004, pp. 27-30.
[2]
H. Guo, J. E. Odegard, M. Lang, R. A. Gopinath, I.W. Selesnick, and C. S. Burrus, “Wavelet based Speckle Reduction with Application to SAR based ATD/R,” First International Conference on Image Processing, 1, 1994, pp. 75-79.
[3]
Maïtine Bergounioux. Quelques méthodes de filtrages en traitement d’image.CIMPA, hal-00512280v1, 2011.
[4]
E. Nezry, Amélioration radiométrique et préservation de la réflectivité radar des images SAR par les filtres de speckle adaptatifs : Théorie et résultats expérimentaux, Centre commun de recherche, Institut des applications de la télédétection, Commission européenne, 1994, pp.3-7.
[5]
J. Philippe, G. Etchegorry, F. Adragna, Y. Kerr, J. Lagouarde, M. Leroy et T. Le Toan, Observation spaciale des paramètres de surface, (Paramètres de surface et signatures spectrales), La télédétection en Francophonie : analyse et perspectives, Edition AUF2000, pp. 299-317.
[6]
N. Allinson, H. Yin, N. Allinson and J. Slack Eds. Self-Organizing Maps.Springer, 2001, pp.95-101.
[7]
T. Kohonen, Essentials of the self-organizing map, Neural Networks 37, 2013, pp. 52–65.
[8]
T. Kohonen, Self-Organizing Maps, Springer Series in Information Sciences, Vol.30, 2°edition, 1997.
[9]
M. Hendel, A. Benyettou, F. Hendel, H. Khilil, « Classification automatique des signaux ECG par les réseaux de neurones probabilistes », "Applications Médicales de l'Informatique : Nouvelles Approches", Monastir-Tunisie, 13, 14 et 15 Novembre 2008.
[10]
R. Le page, Détection et analyse de l’onde P d’un électrocardiogramme : application au dépistage de la fibrillation auriculaire, Thèse Doctorat d’état électronique. L’université de Bretagne occidentale, 2003.
[11]
Teuvo Kohonen, Jussi Hynninen, Jari Kangas and Jorma Laaksonen. Som-pak, the self-organizing map program package. SOM programming team of Helsinki University of Technology, April 1995.
ADDRESS
Science Publishing Group
1 Rockefeller Plaza,
10th and 11th Floors,
New York, NY 10020
U.S.A.
Tel: (001)347-983-5186