Using mutual information to indicate facial poses in video sequences
Georgios Goudelis, Anastasios Tefas, Ioannis Pitas · 2009
Estimation of the facial pose in video sequences is one of the major issues in many vision systems such as face based biometrics, scene understanding for human and others. The proposed method uses a novel pose estimation algorithm based on mutual information to extract any required facial pose from video sequences. The method extracts the poses automatically and classifies them according to view angle. Experimental results on the XM2VTS video database indicated a pose classification rate of 99.2% while it was shown that it outperforms a PCA reconstruction method which was used as a benchmark.