Automatic facial landmark detection in a video sequences of non-manual sign languages

Detection of landmarks in a face is very crucial in facial expression recognition system. It is an easy task for a human being to identify the expression of a person in a particular video sequence but not many efficient fully automated systems are available to perform this task. Face recognition requires the detection of face followed by landmarks identification that serves as a basis in facial expression recognition in a video sequence. Many methods have been given to detect a face in an image efficiently and accurately. But automatic detection of landmarks in each frame of a video sequence is still a difficult task. Most of the system which works on the recognition of facial expression finds the landmarks manually. In this paper a fully automated landmark detection method for the frames in a video sequence is introduced.