Étude comparative de réseaux de neurones pour la reconnaissance des émotions avec les images plénoptiques - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Comparative Study of Neural Networks for Emotion Recognition with Light Field Images

Étude comparative de réseaux de neurones pour la reconnaissance des émotions avec les images plénoptiques

Abstract

In this paper, we present our contribution to facial expression recognition by using image data obtained from the Light Field Face Dataset (LFFD). We compared several neural network architectures which are mainly developed around a convolutional neural network of EfficientNetV2-S and combined with different kinds of recurrent neural networks (LSTM, GRU, BiLSTM and BiGRU). Besides, we exploit different sets of sub-aperture images, each vary in terms of number of images and virtual position. The results show a significant accuracy improvement in two used configurations, depending on the sets of sub-aperture images. The first when using the model of EfficientNetV2-S in two branches configuration and composed with an LSTM. The second uses single branch model with a BiLSTM.
Fichier principal
Vignette du fichier
GRETSI2023_V2.pdf (407.9 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04502467 , version 1 (13-03-2024)

Identifiers

  • HAL Id : hal-04502467 , version 1

Cite

Sabrine Djedjiga, Mohamad Motasem Nawaf, Jean-Marc Boï, Lionel Nicod, Djamal Merad, et al.. Étude comparative de réseaux de neurones pour la reconnaissance des émotions avec les images plénoptiques. Colloque GRETSI-Traitement du Signal et des Images 2023, Aug 2023, Grenoble, France. ⟨hal-04502467⟩
14 View
19 Download

Share

Gmail Mastodon Facebook X LinkedIn More