Accès ouvert

Combining Color Texture and Shape Features In a Multi-Input Convolutional Neural Network for Efficient Face Recognition In Unconstrained Environments

Article scientifique 2023 Anglais

Résumé

Abstract Developing an effective feature representation for face recognition in an un-constrained environment is still a challenging research field. However, in that environment, face images suffer from several issues that could affect the achieved results such as facial expression, occlusion, low resolution, noise, illumination and pose variation. In this paper, an end-to-end multi-input deep convolu-tional neural network architecture was designed for face recognition. The newly designed CNN structure can take full advantage of multi-modal 2D/3D features extracted from face such as: 3DMM-Mesh LBP image, LBPC image, and the face image itself. Through experiments conducted on the LFW, YTF, Multi-PIE, and Bosphorus databases, the obtained results showed a significant improvement compared to traditional state-of-the-art methods which demonstrated the strength of introducing a multi-input convolutional neural network for face recognition in uncontrolled environments.

Citer ce document

Bahroun, S. (2023). Combining Color Texture and Shape Features In a Multi-Input Convolutional Neural Network for Efficient Face Recognition In Unconstrained Environments. https://doi.org/10.21203/rs.3.rs-2944391/v1

Accès au document

Texte intégral en lecture en ligne, réservé aux abonnés SPHAERO et aux membres de l'institution. Se connecter

Voir l'article sur le site de la revue

Auteur(s)

Sahbi Bahroun

Statistiques

Consultations : 1

Téléchargements : 0