Statistical moments based facial expression analysis

Facial expression analysis plays pivotal role for all the applications which are based on emotion recognition. Some of the significant applications are driver alert system, animation, pain monitoring for patients and clinical practices. Emotion recognition is carried out in diverse ways and facial expressions based method is one of the most prominent in non verbal category of emotion recognition. The paper presents detection of all the six universal emotions based on statistical moments i.e. Zernike moments. The features extracted by Zernike moments are further classified through Naïve Bayesian classifier. Rotation Invariance is one of the important properties of Zernike moments which is also experimented. The simulation based experimentation provides average detection accuracy as 81.66% and recognition time less than 2 seconds for frontal face images. The average precision with respect to positives is 81.85 and average sensitivity is obtained as 80.60%. Robustness of system is verified against rotation of images till 360 degrees with step size as 45 degrees. The detection accuracy varies with reference to emotion under consideration but the average accuracy and detection time remains at par with frontal face images.