Pose Discrimination Based on CPCA-SVM in Dynamic System

We present face pose estimate technique. It is based on a machine learning architecture that rapidly estimates pose angles from multi-pose face images. By combining principal component analysis (PCA) of the shape feature and context feature respectively in eigenspace, we can get new eigenvectors to represent the human face pose. Support vector machine (SVM) has the optimal hyperplane that the expected classification error for unseen test samples is minimized. We utilize CPCA-SVM technology to get the optimal results for face pose discrimination. The experiment results demonstrated that the proposed approach is more stable and applicable in dynamic system. Accurate pose discrimination helps to select optimal pose and improve recognition rate in multi-route dynamic face recognition system