Skip to Main content Skip to Navigation
New interface
Conference papers

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.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03789571
Contributor : Matthieu Perreira Da Silva Connect in order to contact the contributor
Submitted on : Tuesday, September 27, 2022 - 3:11:22 PM
Last modification on : Friday, September 30, 2022 - 4:15:57 AM

File

Emotions1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03789571, version 1

Citation

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⟩

Share

Metrics

Record views

16

Files downloads

4