Towards Multi-view and Partially-Occluded Face Alignment
Authors:
- Junliang XingJXJunliang Xing
- Zhiheng NiuZNZhiheng Niu
- Junshi HuangJHJunshi Huang
- Weiming HuWHWeiming Hu
- Shuicheng YanSYShuicheng Yan
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 30 (10636919) , 1829-1836
Abstract
We present a robust model to locate facial landmarks under different views and possibly severe occlusions. To build reliable relationships between face appearance and shape with large view variations, we propose to formulate face alignment as an l1-induced Stagewise Relational Dictionary (SRD) learning problem. During each training stage, the SRD model learns a relational dictionary to capture consistent relationships between face appearance and shape, which are respectively modeled by the pose-indexed image features and the shape displacements for current estimated landmarks. During testing, the SRD model automatically selects a sparse set of the most related shape displacements for the testing face and uses them to refine its shape iteratively. To locate facial landmarks under occlusions, we further propose to learn an occlusion dictionary to model different kinds of partial face occlusions. By deploying the occlusion dictionary into the SRD model, the alignment performance for occluded faces can be further improved. Our algorithm is simple, effective, and easy to implement. Extensive experiments on two benchmark datasets and two newly built datasets have demonstrated its superior performances over the state-of-the-art methods, especially for faces with large view variations and/or occlusions.Keywords
This publication has 23 references indexed in Scilit:
- Dictionary LearningIEEE Signal Processing Magazine, 2011
- Deformable Model Fitting by Regularized Landmark Mean-ShiftInternational Journal of Computer Vision, 2010
- Cascaded pose regression2010
- Facial point detection using boosted regression and graph models2010
- Face Photo-Sketch Synthesis and RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Deformation Modeling for Robust 3D Face MatchingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- A Nonlinear Discriminative Approach to AAM Fitting2007
- Active Appearance Models RevisitedInternational Journal of Computer Vision, 2004
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004