Real Time Detection and Tracking of Mouth Region of Single Human Face

Abstract

For any real-time application, detection and tracking of features becomes very important. The detection and tracking algorithms have to be very robust and efficient with least or zero false positives and false negatives. We use a novel combination for detection and tracking purpose. In this paper we propose a robust mouth region extraction and tracking algorithm that works in real-time. The region of interest for our application requires the face and mouth regions. We propose a novel technique for extracting the mouth region automatically. The proposed technique detects and tracks the mouth in either closed or opened state. We use the color components for skin tone and lips extraction.