Are Facial Expression Recognition Algorithms Reliable in the Context of Interactive Media? A New Metric to Analyse Their Performance - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Are Facial Expression Recognition Algorithms Reliable in the Context of Interactive Media? A New Metric to Analyse Their Performance

Abstract

Emotions, and consequently facial expressions, play an essential role in communication-and thus in everyday life. With the increase of human-machine interactions, and more especially of multimedia applications, automatic recognition of facial expressions has emerged as a challenging task, particularly under naturalistic conditions. In the present work, a benchmark is firstly conducted using four open source deep learning solutions on four labeled image datasets. Thanks to an exhaustive analysis based on two distinct, yet complementary approaches, we show how the four models performed depending on the studied emotions. Furthermore, we present a novel metric based on the Euclidean distance between two given emotions (i.e., ground truth and predicted) to better measure the performance of said models in the context of interactive media, where human sensibility needs to be taken into consideration.
Fichier principal
Vignette du fichier
Emotions1.pdf (5.73 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03789571 , version 1 (27-09-2022)

Identifiers

  • HAL Id : hal-03789571 , version 1

Cite

Emmanuel V.B. Sampaio, Lucie Lévêque, Matthieu Perreira da Silva, Patrick Le Callet. Are Facial Expression Recognition Algorithms Reliable in the Context of Interactive Media? A New Metric to Analyse Their Performance. EmotionIMX: Considering Emotions in Multimedia Experience (ACM IMX 2022 Workshop), Jun 2022, Aveiro, Portugal. ⟨hal-03789571⟩
136 View
187 Download

Share

Gmail Mastodon Facebook X LinkedIn More