Face Tracking Based on 3D Positional Hypothesis

Probabilistic and statistical model analysis methods based on the Bayesian approach have recently been applied to face tracking. Here, we propose a face tracking method based on a Bayesian framework of image sequences. We assume that an observed space is three-dimensional (3D) and model facial shape, rotation and translation in 3D. A 3D positional hypothesis is generated using the facial translation model. The likelihood of facial existence is calculated from the output of the classifier learned using the AdaBoost M1 algorithm. The results of an experiment show the efficiency of the proposed method for face tracking.