Assessing Discriminating Capability of Geometrical Descriptors for 3D Face Recognition by Using the GH-EXIN Neural Network - Université de Picardie Jules Verne Accéder directement au contenu
Chapitre D'ouvrage Année : 2020

Assessing Discriminating Capability of Geometrical Descriptors for 3D Face Recognition by Using the GH-EXIN Neural Network

Résumé

In pattern recognition, neural networks can be used not only for the classification task, but also for feature selection and other intermediate steps. This paper addresses the 3D face recognition problem in order to select the most meaningful geometric descriptors. At this aim, the classification results are directly integrated in a biclustering process in order to select the best leaves of a neural hierarchical tree. This tree is created by a novel neural network GH-EXIN. This approach results in a new criterion for the feature selection. This technique is applied to a database of face expressions where both traditional and novel geometric descriptors are used. The results state the importance of the curvedness novel descriptors and only of a few Euclidean distances.
Fichier non déposé

Dates et versions

hal-03631434 , version 1 (05-04-2022)

Identifiants

Citer

Gabriele Ciravegna, Giansalvo Cirrincione, Federica Marcolin, Pietro Barbiero, Nicole Dagnes, et al.. Assessing Discriminating Capability of Geometrical Descriptors for 3D Face Recognition by Using the GH-EXIN Neural Network. Esposito, A and FaundezZanuy, M and Morabito, FC and Pasero, E. NEURAL APPROACHES TO DYNAMICS OF SIGNAL EXCHANGES, 151, pp.223-233, 2020, Smart Innovation, Systems and Technologies, 978-981-13-8950-4; 978-981-13-8949-8. ⟨10.1007/978-981-13-8950-4\_21⟩. ⟨hal-03631434⟩
22 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More