Automatic Eyewinks Interpretation System Using Face Orientation Recognition for Human-Machine Interface

This paper proposes an automatic face orientation interpretation system for human-machine interface to benefit the severely handicapped people. Its system investigates a new method for movement identification and uses a Hybrid scheme consisting of extracting the Eigen values of covariance matrices using Hough Transform and Bresenham's Raster scan Algorithms. The proposed template matching algorithm has been found effective in tracking the movement of the eyes and, using a classifier it is possible to verify the open or closed eyes and convert the eye winks into a sequence of codes (0 or 1) and subsequently translate the code sequence to a certain valid command.