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.

Document type :
Journal articles
Complete list of metadatas

https://hal-imt.archives-ouvertes.fr/hal-00556162
Contributor : Admin Télécom Paristech <>
Submitted on : Saturday, January 15, 2011 - 4:22:01 PM
Last modification on : Wednesday, February 20, 2019 - 2:41:46 PM

Identifiers

  • HAL Id : hal-00556162, version 1

Collections

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⟩

Share

Metrics

Record views

155