Operating Machines using Facial Expressions

Abstract

   The use of computer systems in general public places like ATM machines, automatic ticket booking systems at metro-stations has become very challenging task due to Covid 19 pandemic. The physical touch might spread the disease. Even at some places like flying airplanes it becomes difficult to operate several switches in parallel by the pilots.  A novel solution is presented in this paper to handle such situation. A hybrid cursor system based on facial movements for hand free control of mouse is presented.  The proposed system has used HAAR algorithm for face detection and make use of facial landmark localization, eye ball tracking, blink detection, mouth aspect ratio to successfully control the mouse. The overall accuracy of the proposed system is 87% and left/right classification accuracy is 94%. The keyboard control through facial control could be done using the same approach.