Accéder directement au contenu Accéder directement à la navigation
Article dans une revue

Fuzzy Fusion System for Radar Target Recognition

Imen Jdey 1, 2 Abdelmalek Toumi 3 Ali Khenchaf 4 Mounir Dhibi 2, 5 M.S Bouhlel 2, 5
3 Lab-STICC_ENSTAB_CID_TOMS;REMS
STIC - Pôle STIC [Brest], Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
4 Lab-STICC_ENSTAB_MOM_PIM ; REMS
STIC - Pôle STIC [Brest], Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : Complex target recognition tasks rarely succeed through the application of just one classification scheme. Using the combination/fusion of different classifiers based on Inverse Synthetic Aperture Radar (ISAR) images usually explore complementary information. Thus, the each individual classifier results will be combined in order to improve the global recognition rate. Automatic target recognition systems mostly employ fusion strategies for this aim. The empirical evidence of the effectiveness of this approach makes it of the main current directions in target recognition research. In this paper, the recognition combination will be presented using fuzzy fusion based on three classifiers: K- nearest Neighbors, Support Vector Machines and Multi-Layer Perceptron classifiers. In this purpose, we have used Sugeno and Mamdani models. To improve our approach, we have used an ISAR image database which was reconstructed from an anechoic chamber. All results of all individual and combined classifiers will be presented.
Liste complète des métadonnées

https://hal-ensta-bretagne.archives-ouvertes.fr/hal-00777095
Contributeur : Annick Billon-Coat <>
Soumis le : mercredi 16 janvier 2013 - 17:21:35
Dernière modification le : mercredi 24 juin 2020 - 16:19:29

Identifiants

  • HAL Id : hal-00777095, version 1

Citation

Imen Jdey, Abdelmalek Toumi, Ali Khenchaf, Mounir Dhibi, M.S Bouhlel. Fuzzy Fusion System for Radar Target Recognition. International Journal of Computer Applications & Information Technology, 2012, 1 (3), pp.136-142. ⟨hal-00777095⟩

Partager

Métriques

Consultations de la notice

423