Semantic Annotation of Satellite Images using Latent Dirichlet Allocation

Abstract :

We a use a semantic learning model to affect user oriented names to satellite image regions. After a supervised classification method of training subsets, we proceed to an automatic labeling by use of a Latent Dirichlet Allocation method (LDA) which does not take into consideration the adjacency relationship between visual words.

Type de document :
Article dans une revue
IEEE Geoscience and Remote Sensing Letters, IEEE - Institute of Electrical and Electronics Engineers, 2010, 7 (1), pp.28-32
Liste complète des métadonnées

https://hal-imt.archives-ouvertes.fr/hal-00556162
Contributeur : Admin Télécom Paristech <>
Soumis le : samedi 15 janvier 2011 - 16:22:01
Dernière modification le : jeudi 11 janvier 2018 - 06:23:38

Identifiants

  • HAL Id : hal-00556162, version 1

Citation

M. Lienou, M. Datcu, H. Maître. Semantic Annotation of Satellite Images using Latent Dirichlet Allocation. IEEE Geoscience and Remote Sensing Letters, IEEE - Institute of Electrical and Electronics Engineers, 2010, 7 (1), pp.28-32. 〈hal-00556162〉

Partager

Métriques

Consultations de la notice

112