Occlusion-Free Face Alignment: Deep Regression Networks Coupled with De-Corrupt AutoEncoders
Authors:
- Jie ZhangJZJie Zhang
- Meina KanMKMeina Kan
- Shiguang ShanSSShiguang Shan
- Xilin ChenXCXilin Chen
- 1 June 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3428-3437
Abstract
Face alignment or facial landmark detection plays an important role in many computer vision applications, e.g., face recognition, facial expression recognition, face animation, etc. However, the performance of face alignment system degenerates severely when occlusions occur. In this work, we propose a novel face alignment method, which cascades several Deep Regression networks coupled with De-corrupt Autoencoders (denoted as DRDA) to explicitly handle partial occlusion problem. Different from the previous works that can only detect occlusions and discard the occluded parts, our proposed de-corrupt autoencoder network can automatically recover the genuine appearance for the occluded parts and the recovered parts can be leveraged together with those non-occluded parts for more accurate alignment. By coupling de-corrupt autoencoders with deep regression networks, a deep alignment model robust to partial occlusions is achieved. Besides, our method can localize occluded regions rather than merely predict whether the landmarks are occluded. Experiments on two challenging occluded face datasets demonstrate that our method significantly outperforms the state-of-the-art methods.Keywords
This publication has 29 references indexed in Scilit:
- Global supervised descent method2015
- Random Cascaded-Regression Copse for Robust Facial Landmark DetectionIEEE Signal Processing Letters, 2014
- Gauss-Newton Deformable Part Models for Face Alignment In-the-Wild2014
- Towards Multi-view and Partially-Occluded Face Alignment2014
- Pose-Free Facial Landmark Fitting via Optimized Part Mixtures and Cascaded Deformable Shape Model2013
- Supervised Descent Method and Its Applications to Face Alignment2013
- Facial Feature Tracking Under Varying Facial Expressions and Face Poses Based on Restricted Boltzmann Machines2013
- Real-time facial feature detection using conditional regression forests2012
- Cascaded pose regression2010
- Extracting and composing robust features with denoising autoencoders2008