Full text: Proceedings, XXth congress (Part 7)

2004 
2 for 
from 
and 
ISSN 
Less- 
nable 
zell P 
Policy 
osion. 
3 and 
ystem 
Space 
vledge 
| land 
553. 
insion, 
in the 
egies 
Secher 
Sahel 
N: 55- 
ition 
Land- 
age of 
1 and 
ensing 
al IRS- 
mabad 
in. 
ang on 
of Rio 
1: 115- 
ability 
] Land 
X Soil, 
in poor 
ies and 
use. In: 
erty and 
3 
igement 
oratory 
pology. 
rgia. 
fication 
es. 15: 
A GAMMA-CONVERGENCE APPLIED TO MULTISPECTRAL IMAGE 
CLASSIFICATION AND RESTORATION 
M.Iddir Zait *', Y.Smara ^ 
* INI National Institute of Computing Science , BP 68M Oued Smar Algiers Algeria - m_iddir@ini.dz 
malika_iddir@yahoo.fr 
° Laboratory of image processing and radiation, university of Sciences et Technologies Houari Boumedienne, BP32 
El-Alia Bab-Ezzouar 16111 Algiers Algeria- y.smara@mailcity.com 
PS WG VII/1 
KEY WORDS: Image Classification, Image Restoration, Multispectral satellite image, Remote Sensing, Variational model. 
ABSTRACT: 
The main objective of this paper is to develop a model which combines in the same process image classification and restoration. 
Image classification consists of assigning a label to each site of an image to produce a partition into homogeneous labeled areas. The 
classification problem concerns many applications, like in the field of remote sensing: land use management, monitoring, urban 
areas. 
Observed images are often affected by degradations. The purpose of restoration is to find an original image describing a real scene 
from the observed one. This problem can be identified by inverse problem. In general, it is ill-posed in the sense of Hadamard. The 
existence and uniqueness of the solution are not guaranteed. It is therefore necessary to introduce an a priori constraint on the 
solution. This operation is the regularization. We can distinguish two types of regularization: the linear one and the non-linear. In 
this paper, we develop a model proposed by C.Samson, combining classification and restoration with non linear regularization. It's 
based on works developed for phase transitions in fluid mechanics by Van der Walls-Cahn-Hilliard, and uses a Gamma-convergence 
theory. This model is named variational model, due to the fact that calculus of variations is its main tool. The classification- 
restoration is obtained by minimizing a sequence of functionals. The result is a classified and restored image, and corresponds to an 
image composed of homogeneous classes, separated by minimum length boundaries. The minimization problem is transformed by 
Euler-Lagrange equations into PDEs (Partial Differential Equations) resolution problem. ; 
We have experimented this model on synthetic and satellite images. For real images, we have considered images from SPOT-1 
satellite representing the regions of Blida in south-west of Algiers (capital of Algeria). We will discuss at the end of the paper the 
results we have obtained. 
RESUME : 
L'objectif principal de ce papier est développer un modéle qui combine dans un méme processus une opération de classification 
d'image et une opération de restauration. La classification consiste partitionner une image en régions repérées par des étiquettes 
différentes. Le probléme de classification concerne beaucoup d'applications telles que la gestion de la couverture terrestre en 
télédetection, le suivi de l'urbanisation etc... 
Les images observées sont souvent dégradées. Le but de la restauration est de retrouver l'image originale à partir de celle observée. 
Ce probléme est un probléme inverse mal posé au sens d'Hadamard. L'existence et l'unicité de la solution ne sont pas assurées. Il est 
alors nécessaire de régulariser la solution par l'introduction d'un a priori. Nous pouvons distinguer deux types de régularisation: 
linéaire et  non-linéaire. Dans ce papier, nous développons un modèle variationnel, proposé par C.Samson, qui combine 
classification et restauration avec une régularisation non linéaire. Il est basé sur les travaux de Van der walls Cahn-Hilliard 
développés pour les transitions de phase en mécanique des fluides, et utilise la théorie de la Gamma Convergence. La classification 
restauration est obtenue en minimisant une séquence de fonctionnelles. Le résultat correspond à une image composée de classes 
homogènes séparées par des interfaces de longueur minimales. Le problème de minimisation est transformé par les équations 
d’Euler-Lagrange en un problème de résolution d’équations aux dérivées partielles (EDP). 
Nous avons testé ce modèle sur des images de synthèse et sur des images satellitaires de la série SPOT-1 recouvrant la région de 
Blida dans sud est d'Alger (capital d'Algérie). Nous présenterons à la fin du papier les résultats obtenus. 
For the extraction of the thematic information of the remote 
sensed images, the classification proves to be an inescapable 
1. INTRODUCTION tool. It consists in achieving a partition of the image into 
labeled regions. We can distinguish two types of classification: 
The remote sensing is a multidisciplinary science that knows the supervised classification for which the number of classes 
actually a real flight, with the use of sensors embarked more and their parameters are known beforehand, and the non 
and more sensitive and more and more varied. 
1209 
 
	        
Waiting...

Note to user

Dear user,

In response to current developments in the web technology used by the Goobi viewer, the software no longer supports your browser.

Please use one of the following browsers to display this page correctly.

Thank you.