Application of projection learning to the detection of urban areas in SPOT satellite images

Konrad Weigl 1 Gerard Giraudon 1 Marc Berthod 1
1 PASTIS - Scene Analysis and Symbolic Image Processing
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : We introduce a novel learning algorithm for neural networks, with the major feature of being rapid when compared to classical learning algorithms, offering misclassification rates of 5% and less after only a few iterations, i.e. 20-30 seconds of learning, depending on the task, if a suitable preprocessing has been done. The algorithm is based on considering a neural network as a base in function space, base onto which the function to be learned is projected. We thus call our algorithm projection learning. We present the algorithm, show the application to the detection of inhabited areas in satellite images, discuss the various preprocessors used, compare to other approaches used and outline further directions or research.
Type de document :
Rapport
[Research Report] RR-2143, INRIA. 1993
Liste complète des métadonnées

https://hal.inria.fr/inria-00074529
Contributeur : Rapport de Recherche Inria <>
Soumis le : mercredi 24 mai 2006 - 15:41:03
Dernière modification le : samedi 27 janvier 2018 - 01:31:28
Document(s) archivé(s) le : dimanche 4 avril 2010 - 22:19:08

Fichiers

Identifiants

  • HAL Id : inria-00074529, version 1

Collections

Citation

Konrad Weigl, Gerard Giraudon, Marc Berthod. Application of projection learning to the detection of urban areas in SPOT satellite images. [Research Report] RR-2143, INRIA. 1993. 〈inria-00074529〉

Partager

Métriques

Consultations de la notice

113

Téléchargements de fichiers

110