Incremental Principal Component Analysis-Based Sparse Representation for Face Pose Classification

This paper proposes an Adaptive Sparse Representation pose Classification (ASRC) algorithm to deal with face pose estimation in occlusion, bad illumination and low-resolution cases. The proposed approach classifies different poses, the appearance of face images from the same pose being modelled by an online eigenspace which is built via Incremental Principal Component Analysis. Then the combination of the eigenspaces of all pose classes are used as an over-complete dictionary for sparse representation and classification. However, the big amount of training images may lead to build an extremely large dictionary which will decelerate the classification procedure. To avoid this situation, we devise a conditional update method that updates the training eigenspace only with the misclassified face images. Experimental results show that the proposed method is very robust when the illumination condition changes very dynamically and image resolutions are quite poor.

[1]  Mohan M. Trivedi,et al.  Head Pose Estimation for Driver Assistance Systems: A Robust Algorithm and Experimental Evaluation , 2007, 2007 IEEE Intelligent Transportation Systems Conference.

[2]  M. Saquib Sarfraz,et al.  Head Pose Estimation in Face Recognition Across Pose Scenarios , 2008, VISAPP.

[3]  Mohan M. Trivedi,et al.  Head Pose Estimation in Computer Vision: A Survey , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Ian D. Reid,et al.  Colour Invariant Head Pose Classification in Low Resolution Video , 2008, BMVC.

[5]  Nec Labratories America.  ESTIMATING FACIAL POSE FROM A SPARSE REPRESENTATION , 2004 .

[6]  Fei Su,et al.  Robust head pose estimation via Convex Regularized Sparse Regression , 2011, 2011 18th IEEE International Conference on Image Processing.

[7]  Hankyu Moon,et al.  Estimating facial pose from a sparse representation [face recognition applications] , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[8]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  D. Donoho.  For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution , 2006 .

[10]  Ying Wu,et al.  Query Driven Localized Linear Discriminant Models for Head Pose Estimation , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[11]  Horst Bischof,et al.  Supervised local subspace learning for continuous head pose estimation , 2011, CVPR 2011.

[12]  Ralph R. Martin,et al.  Incremental Eigenanalysis for Classification , 1998, BMVC.

[13]  Paul A. Viola,et al.  Robust Real-time Object Detection , 2001 .

[14]  Ehud Rivlin,et al.  Robust 3D Head Tracking Using Camera Pose Estimation , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[15]  Shaogang Gong,et al.  Head Pose Classification in Crowded Scenes , 2009, BMVC.

[16]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[17]  Terence Sim,et al.  The CMU Pose, Illumination, and Expression Database , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Simon Baker,et al.  Active Appearance Models Revisited , 2004, International Journal of Computer Vision.

[19]  Sethuraman Panchanathan,et al.  Biased Manifold Embedding: A Framework for Person-Independent Head Pose Estimation , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Thomas S. Huang,et al.  Calibrating Head Pose Estimation in Videos for Meeting Room Event Analysis , 2006, 2006 International Conference on Image Processing.