Kalman filter tracking for facial expression recognition using noticeable feature selection

In this work we develop a fast facial expression recognition system with low complexity by proposing a method that does not need face detection for facial characteristics tracking. Moreover, our simple feature selection differentiates between the expressions and accelerates the systempsilas performance. In this system, selected facial feature points from the first frame to the last are tracked automatically using a maximum cross-correlation algorithm followed by Kalman Filter. The extracted feature vector is then given to different classifiers to classify the face expressions within six basic emotions (happiness, surprise, sadness, disgust, fear and anger). For Cohn-Kanade database, the best result is obtained by Bayes optimal classifier with the average correct classification rate (Ave-CCR) of 93.72 percent.