Unconstrained Human face Tracking in live Video

Abstract

In surveillance applications visual face detection and tracking becomes an essential task. Many algorithms and technologies have been developed to automatically monitor pedestrians or other moving objects and to track the detected face. One main difficulty in face tracking, among many others, is to choose suitable features and models for detecting and tracking the target. For tracking of faces there are some common features are considered like color, intensity, shape and feature points. In this paper we discuss about mean shift based face tracking based on the color, optical flow tracking based on the intensity and motion, SIFT face tracking based on scale invariant local feature points. Mean shift is then combined with local feature points. Initial results from tries have shown that the implemented method is able to track target face with different pose variation, rotation, partial occlusion and deformation.