Accurate Landmarking of Three-Dimensional FacialData in the Presence of Facial Expressions andOcclusions Using a Three-DimensionalStatistical Facial Feature Model - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics Year : 2011

Accurate Landmarking of Three-Dimensional FacialData in the Presence of Facial Expressions andOcclusions Using a Three-DimensionalStatistical Facial Feature Model

Abstract

Three-dimensional face landmarking aims at automatically localizing facial landmarks and has a wide range of applications (e.g., face recognition, face tracking, and facial expression analysis). Existing methods assume neutral facial expressions and unoccluded faces. In this paper, we propose a general learning-based framework for reliable landmark localization on 3-D facial data under challenging conditions (i.e., facial expressions and occlusions). Our approach relies on a statistical model, called 3-D statistical facial feature model, which learns both the global variations in configurational relationships between landmarks and the local variations of texture and geometry around each landmark. Based on this model, we further propose an occlusion classifier and a fitting algorithm. Results from experiments on three publicly available 3-D face databases (FRGC, BU-3-DFE, and Bosphorus) demonstrate the effectiveness of our approach, in terms of landmarking accuracy and robustness, in the presence of expressions and occlusions.
No file

Dates and versions

hal-01354433 , version 1 (18-08-2016)

Identifiers

Cite

Xi Zhao, Emmanuel Dellandréa, Liming Chen, Ioannis A. Kakadiaris. Accurate Landmarking of Three-Dimensional FacialData in the Presence of Facial Expressions andOcclusions Using a Three-DimensionalStatistical Facial Feature Model. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2011, 5, 41, pp.1417-1428. ⟨10.1109/TSMCB.2011.2148711⟩. ⟨hal-01354433⟩
72 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More