Assistance for Paralyzed Patient Using Eye Motion Detection

The objective of this paper is to propose a human computer interface for a completely paralyzed patient using eye motion and eye blink detection. In paralysis the ability to control muscles movement is limited around the eye muscles or blinks are the only way for the patient to communicate. In such communication the interface is often intrusive, which require special hardware or depend on active infrared sensors. A nonintrusive communication interface which was developed and runs on a consumer grade computer which takes input in the form of video frames from an inexpensive webcam without special lightning conditions. The interface detects voluntary eye blinks and pupil motion then interprets them as control commands. The detected eye direction can be useful through applications such as medical assistance, S.O.S, basic utility. The video frame is processed by OpenCV library which is an open source software.