Skip to Main content Skip to Navigation
Conference papers

Precise 2.5D Facial Landmarking via an Analysis by Synthesis approach

Xi Zhao 1 Przemyslaw Szeptycki 1 Emmanuel Dellandréa 1 Liming Chen 1 
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : 3D face landmarking aims at automatic localization of 3D facial features and has a wide range of applications, including face recognition, face tracking, facial expression analysis. Methods so far developed for pure 2D texture images were shown sensitive to lighting condition changes. In this paper, we present a 3D statistical model-based technique for accurate 3D face landmarking, thus using an "analysis by synthesis" approach. Our 3D statistical model learns from a training set both variations of global 3D face shapes as well as the local ones in terms of scale-free texture and range patches around each landmark. When fitted for a best match to a new 3D face model for analysis, this 3D statistical model delivers the location of the landmarks on the input 3D face model. Experimented on more than 1860 face models from FRGC datasets, our method achieves an average of locating errors less than 7mm for 15 feature points. Compared with a curvature analysis-based method also developed within our team, this learning-based method enables localization of more face landmarks with a general better accuracy at the cost of a learning step.
Document type :
Conference papers
Complete list of metadata
Contributor : Équipe gestionnaire des publications SI LIRIS Connect in order to contact the contributor
Submitted on : Tuesday, January 17, 2017 - 1:59:31 PM
Last modification on : Tuesday, June 1, 2021 - 2:08:09 PM



Xi Zhao, Przemyslaw Szeptycki, Emmanuel Dellandréa, Liming Chen. Precise 2.5D Facial Landmarking via an Analysis by Synthesis approach. 2009 IEEE Workshop on Applications of Computer Vision (WACV 2009) , Sep 2009, Snowbird, Utah, United States. pp.1-7, ⟨10.1109/WACV.2009.5403102⟩. ⟨hal-01437790⟩



Record views