Skip to Main content Skip to Navigation
Theses

INFÉRENCE DE CONNAISSANCES SÉMANTIQUES, APPLICATION AUX IMAGES SATELLITAIRES

Abstract : A novel method is presented for annotating satellite images. The labels used for annotation are given by a user with a set of example images. A learning step is then applied to learn the model. The originality of the method is to formulate the problem of semantic annotation to a further extent than a mere probabilistic classification task. The method takes into account the semantical relationship between the concepts by considering a duality between the structure of the model and the structure of the set of labels. The semantical structure of the labels is represented by a semantic network containing three semantical relationships: synonymy, meronymy, and hyponymy. The semantic network is constrained in a hierarchy induced by the links of hyponymy and meronymy. By a procedure of MDL model selection, it is possible to find the optimal semantical structure of the set of labels. This method has been evaluated on SPOT5 and Quickbird databases.
Document type :
Theses
Complete list of metadatas

Cited literature [138 references]  Display  Hide  Download

https://pastel.archives-ouvertes.fr/pastel-00556842
Contributor : Jean-Baptiste Bordes <>
Submitted on : Monday, January 17, 2011 - 9:53:02 PM
Last modification on : Friday, July 31, 2020 - 10:44:07 AM
Long-term archiving on: : Saturday, December 3, 2016 - 2:39:38 AM

Identifiers

  • HAL Id : pastel-00556842, version 1

Collections

Citation

Jean-Baptiste Bordes. INFÉRENCE DE CONNAISSANCES SÉMANTIQUES, APPLICATION AUX IMAGES SATELLITAIRES. Traitement des images [eess.IV]. Télécom ParisTech, 2009. Français. ⟨pastel-00556842v1⟩

Share

Metrics

Record views

517

Files downloads

2363