Facial expression recognition using light field cameras : a comparative study of deep learning architectures - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Facial expression recognition using light field cameras : a comparative study of deep learning architectures

Résumé

This paper presents our contribution to facial expression recognition using images obtained from the Light Field Face Dataset(LF). We compare several variants of neural network architectures to demonstrate the potential benefits of using this relatively new optical system in the field of facial expres- sion recognition. We propose the use of the EfficientNetV2-S convolutional neural network as the base architecture, combined with various recurrent neural networks (LSTM, GRU, BiLSTM, and BiGRU) in our experiments. Furthermore, we investigate different sets of sub-aperture images, each varying in terms of the number of images and virtual position. The results demonstrate a significant improvement in accuracy for two specific configurations, depending on the sets of subaperture images used. The first configuration involves using the EfficientNetV2-S model in a two-branch configuration combined with an LSTM. The second configuration uses a single branch model with a BiLSTM.
Fichier principal
Vignette du fichier
ICIP2023_V4.pdf (521.88 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04311079 , version 1 (15-04-2024)

Identifiants

  • HAL Id : hal-04311079 , version 1

Citer

Sabrine Oucherif, Lionel Nicod, Mohamad Nataf, Jean-Marc Boi, Djamal Merad, et al.. Facial expression recognition using light field cameras : a comparative study of deep learning architectures. International Conference on Image Processing, Oct 2023, Kuala Lumpur, France. ⟨hal-04311079⟩
19 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More