Towards Spatio-Temporal Face Alignment in Unconstrained Conditions

Romain Belmonte (1, 2) , Nacim Ihaddadene (1) , Pierre Tirilly (3) , Chaabane Djeraba (3) , Ioan Marius Bilasco (4)

1 ISEN-Lille - Institut Supérieur de l'Electronique et du Numérique - Lille
2 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
3 LIFL - FOX MIIRE
4 Université de Lille, Sciences et Technologies

Face alignment is an essential task for many applications. Its objective is to locate feature points on the face, in order to identify its geometric structure. Under unconstrained conditions, the different variations that may occur in the visual context, together with the instability of face detection, make it a difficult problem to solve. While many methods have been proposed, their performances under these constraints are still not satisfactory. In this article, we claim that face alignment should be studied using image sequences rather than still images, as it has been done so far. We show the importance of taking into consideration the temporal information under unconstrained conditions.

Mots clés: Face Alignment; Spatio-Temporal Models; Landmark Localization; Unconstrained Conditions; Video-based

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Romain Belmonte, Nacim Ihaddadene, Pierre Tirilly, Chaabane Djeraba, Ioan Marius Bilasco. Towards Spatio-Temporal Face Alignment in Unconstrained Conditions. VISAPP, Jan 2018, Funchal, Portugal. ⟨hal-01644813⟩