Impact of Facial Landmark Localization on Facial Expression Recognition

Belmonte, Romain; Allaert, Benjamin; Tirilly, Pierre; Bilasco, Ioan Marius; Djeraba, Chaabane; Sebe, Niculae

Document type :

Compte-rendu et recension critique d'ouvrage

DOI :

10.1109/TAFFC.2021.3124142

Title :

Impact of Facial Landmark Localization on Facial Expression Recognition

Author(s) :

Belmonte, Romain [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Allaert, Benjamin [Auteur]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Nord Europe]
Centre for Digital Systems [CERI SN - IMT Nord Europe]
Tirilly, Pierre [Auteur]

Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Bilasco, Ioan Marius [Auteur]

FOX MIIRE [LIFL]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Djeraba, Chaabane [Auteur]

Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sebe, Niculae [Auteur]
Università degli Studi di Trento = University of Trento [UNITN]

Journal title :

IEEE Transactions on Affective Computing

Pages :

1267 - 1279

Publisher :

Institute of Electrical and Electronics Engineers

Publication date :

2021

ISSN :

1949-3045

English keyword(s) :

facial landmark localization
face registration
facial expression recognition

HAL domain(s) :

Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]

English abstract : [en]

Although facial landmark localization (FLL) approaches are becoming increasingly accurate in identifying facial components, one question remains unanswered: what is the impact of these approaches on subsequent, related ...
Show more >Although facial landmark localization (FLL) approaches are becoming increasingly accurate in identifying facial components, one question remains unanswered: what is the impact of these approaches on subsequent, related tasks? In this paper, we focus on facial expression recognition (FER), where facial landmarks are used for face registration, which is a common usage. Since the common datasets for facial landmark localization do not allow for a proper measurement of performance according to the different difficulties (e.g., pose, expression, illumination, occlusion, motion blur), we also quantify the performance of recent approaches in the presence of head pose variations and facial expressions. Finally, we conduct a study of the impact of these approaches on FER. We show that the landmark accuracy achieved so far by optimizing the euclidean distance does not necessarily guarantee a gain in performance for FER. To deal with this issue, we propose a new evaluation metric for FLL that is more relevant to FER.Show less >

Language :

Anglais

Popular science :

Non

Collections :