A Neural Network Model for Solving the Feature Correspondence Problem - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

A Neural Network Model for Solving the Feature Correspondence Problem

Ala Aboudib
  • Fonction : Auteur
  • PersonId : 959300
Gilles Coppin

Résumé

Finding correspondences between image features is a fundamental question in computer vision. Many models in literature have proposed to view this as a graph matching problem whose solution can be approximated using optimization principles. In this paper, we propose a different treatment of this problem from a neural network perspective. We present a new model for matching features inspired by the architecture of a recently introduced neural network. We show that by using popular neural network principles like max-pooling, k-winners-take-all and iterative processing, we obtain a better accuracy at matching features in cluttered environments. The proposed solution is accompanied by an experimental evaluation and is compared to state-of-the-art models.
Fichier non déposé

Dates et versions

hal-01371020 , version 1 (23-09-2016)

Identifiants

Citer

Ala Aboudib, Vincent Gripon, Gilles Coppin. A Neural Network Model for Solving the Feature Correspondence Problem. ICANN 2016 : 25th International Conference on Artificial Neural Networks, Sep 2016, Barcelone, Spain. pp.439 - 446, ⟨10.1007/978-3-319-44781-0_52⟩. ⟨hal-01371020⟩
57 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More