Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Deep CNN for 3D Face Recognition

Abstract : Three dimensional face analysis is being widely investigated since it appears as a robust solution to overcome the limits of two dimensional technologies. 3D methods allow to relate the recognition process on features not depending on lightning, head poses, make up and occlusions. This paper proposes a new approach to the problem consisting of a novel image representation, where specific facial descriptors replace the RGB traditional channels and a convolutional neural network performs the classification. We chose to use MobileNetV2, a relatively new network, as it has a low amount of parameters to train. The method has been evaluated on the Bosphorus database, and even though it is still a preliminary study, the results obtained with our method are extremely encouraging; the recognition rate achieved is 97.560% and it is comparable to the state of the art. This result, reached despite the fact that the Bosphorus database has a great number of subjects (105) but a low number of scans (4666), shows the effectiveness of this representation combined with convolutional neural networks.
Type de document :
Communication dans un congrès
Liste complète des métadonnées
Contributeur : Louise DESSAIVRE Connectez-vous pour contacter le contributeur
Soumis le : mardi 5 avril 2022 - 16:25:13
Dernière modification le : vendredi 5 août 2022 - 11:21:49




Elena Carlotta Olivetti, Jacopo Ferretti, Giansalvo Cirrincione, Francesca Nonis, Stefano Tornincasa, et al.. Deep CNN for 3D Face Recognition. DESIGN TOOLS AND METHODS IN INDUSTRIAL ENGINEERING, ADM 2019, Sep 2019, Modena, Italy. pp.665-674, ⟨10.1007/978-3-030-31154-4\_56⟩. ⟨hal-03631439⟩



Consultations de la notice