P.K. Biswas and M. Pandit (Germany)
Video Segmentation, Optical Flow, Active Contour Model, Tracking.
Face segmentation is one of the most important tasks in
Model Based Video coding for Video Telephony and
Video Conferencing applications. Since the face
movement is usually different from the back ground
movement, derivative of the optical flow field gives
useful hints for the region of the image frame
containing human face. In this work we have used a
modified Active Contour Model, where derivative of
the optical flow field is used as a component of the
energy function to be minimized, to segment out the
face from video sequence. Experiments with a number
of test sequences give encouraging results.