Face Recognition With Pose Variations and Misalignment via Orthogonal Procrustes Regression

• Published in: IEEE transactions on image processing 2016-06, Vol.25 (6), p.2673-2683
• Main Authors: Tai, Ying, Yang, Jian, Zhang, Yigong, Luo, Lei, Qian, Jianjun, Chen, Yu
• Format: Article
• Language: English
• Subjects: Algorithms; Collaboration; Databases, Factual; Face; face alignment; Face recognition; Humans; Linear Models; Manifolds; orthogonal Procrustes problem (OPP); Pattern Recognition, Automated; pose variations; Regression analysis; Training
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2016.2551362

A linear regression-based method is a hot topic in face recognition community. Recently, sparse representation and collaborative representation-based classifiers for face recognition have been proposed and attracted great attention. However, most of the existing regression analysis-based methods are sensitive to pose variations. In this paper, we introduce the orthogonal Procrustes problem (OPP) as a model to handle pose variations existed in 2D face images. OPP seeks an optimal linear transformation between two images with different poses so as to make the transformed image best fits the other one. We integrate OPP into the regression model and propose the orthogonal Procrustes regression (OPR) model. To address the problem that the linear transformation is not suitable for handling highly non-linear pose variation, we further adopt a progressive strategy and propose the stacked OPR. As a practical framework, OPR can handle face alignment, pose correction, and face representation simultaneously. We optimize the proposed model via an efficient alternating iterative algorithm, and experimental results on three popular face databases, such as CMU PIE database, CMU Multi-PIE database, and LFW database, demonstrate the effectiveness of our proposed method.