Comparisons of local methods for face alignment

Exploring relations among different local methods for face alignment is a problem to be solved crucially. It is of significance for face recognition and face tracking. In this study, a general framework for local face alignment is presented. On this basis, three classical methods are described, i.e. method using structured support vector machine, that using regularised landmark mean-shift (RLMS), and that using multiview and mixtures of trees. Comparisons of performance among different methods are carried out on four datasets, i.e. BioID, LFW, Helen, and LFPW. For each face, five facial landmarks are used, i.e. tip of nose, inner corner of left eye, inner corner of right eye, left mouth corner, and right mouth corner. Average alignment time and average alignment precision are used as metrics. Test results show that methods using RLMS have better performance on the whole.

[1]  David Cristinacce,et al.  Automatic feature localisation with constrained local models , 2008, Pattern Recognit..

[2]  David J. Kriegman,et al.  Localizing parts of faces using a consensus of exemplars , 2011, CVPR.

[3]  Václav Hlavác,et al.  Facial Landmarks Detector Learned by the Structured Output SVM , 2012, VISIGRAPP.

[4]  Stefanos Zafeiriou,et al.  300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[5]  Klaus J. Kirchberg,et al.  Robust Face Detection Using the Hausdorff Distance , 2001, AVBPA.

[6]  Thomas S. Huang,et al.  Interactive Facial Feature Localization , 2012, ECCV.

[7]  Xiaogang Wang,et al.  Deep Convolutional Network Cascade for Facial Point Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Luc Van Gool,et al.  Real-time facial feature detection using conditional regression forests , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Simon Lucey,et al.  Deformable Model Fitting by Regularized Landmark Mean-Shift , 2010, International Journal of Computer Vision.

[11]  Timothy F. Cootes,et al.  Feature Detection and Tracking with Constrained Local Models , 2006, BMVC.

[12]  Jian Sun,et al.  Face Alignment at 3000 FPS via Regressing Local Binary Features , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Deva Ramanan,et al.  Face detection, pose estimation, and landmark localization in the wild , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Xiaoou Tang,et al.  Facial Landmark Detection by Deep Multi-task Learning , 2014, ECCV.

[15]  Xiaogang Wang,et al.  Hierarchical face parsing via deep learning , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Fernando De la Torre,et al.  Supervised Descent Method and Its Applications to Face Alignment , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Josephine Sullivan,et al.  One millisecond face alignment with an ensemble of regression trees , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Mikkel B. Stegmann,et al.  Active appearance models: Theory and cases , 2000 .

[19]  Shiguang Shan,et al.  Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment , 2014, ECCV.

[20]  Qiang Ji,et al.  Robust Facial Landmark Detection Under Significant Head Poses and Occlusion , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[21]  Yang Wang,et al.  Enforcing convexity for improved alignment with constrained local models , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Jian Sun,et al.  Face Alignment by Explicit Shape Regression , 2012, International Journal of Computer Vision.