Face Recognition and Tracking Methods Based on the Python

Facial expression recognition is necessary for designing any realistic human-machine interfaces. Previous published facial expression recognition systems achieved goodrecognition rates, but most of them performed well only when the user look at the camera. In this study, we propose a new method for robust, view-independent recognition of facial expressions that does not make this assumption. The system can use 3-D model-based tracker to extract every frame of a monocular video sequence simultaneously. There are two main contributions of this paper. First, we demonstrate that the information extracted through tracking enables robust facial expression recognition in spite of large rotational head movements. Second, we show that Support Vector Machine is a suitable engine for robust classification. Recognition rates ashigh as 91 percent are achieved in classifying distinct dynamic facial motions (neutral, opening/closing mouth, smile, raising eyebrow).

Keywords:

face recognition , image processing , python , tracking