INTRODUCTION
Eye tracking is a technique whereby an individual’s eye movements are measured so that the researcher knows both where a person is looking at any given time and the sequence in which their eyes are shifting from one location to another. The annual report of the Ministry of Public Health and Welfare states that 0.73 million people have a motor disability on the legs and arms [8]. For people with these disabilities, many different kinds of electrical and robotic wheelchairs have been designed. These people have problems to use a conventional wheelchair. A recent clinical survey [1] indicated that 9%–10% of patients who received power wheelchair training found it extremely difficult or impossible to use it for their activities of daily living, and 40% of patients found the steering and maneuvering tasks difficult or impossible. These people are dependent upon others to push them, so often feel powerless and out of control [3]. So, an eye tracking system is proposed here.
2. EYE MOVEMENT TRACKING
Eye movement tracking is used in this project to determine the motion of eye. Based on this direction of motion of eye, commands are given to an electrically driven wheelchair. The eye motion tracking hardware includes a USB web camera which is mounted on a cap worn by the user. This camera is adjusted so that it lies in front of one of the eye of user. The camera has inbuilt light source, so that it can capture bright images if darkness appears under the cap. The drivers of the camera are installed in a PC to which the camera is plugged in. The software module for image processing works on three different modules: video capturing, frame extraction and pixel color detection. The image processing program performs these three steps based on the coherence algorithm explained below.
2.1. Coherence Algorithm
The coherence algorithm works for detecting the motion of eye. This algorithm operates on the frames extracted from the video of the eye. From the frame, the algorithm extracts the pixels which lie on the vertical edges of the rectangular area selected by the user. These pixels are then processed to determine the RGB values. When the user is looking straight in font, the pixels on both the vertical lines are black. This is interpreted as the “center” direction of the user’s eye. When user looks towards left, the pixels on the left vertical line are black, but the pixels on the right vertical line are white. This can be seen in the Fig. 1 shown below. The closed eye condition is also recognized by the software. This condition is then used to determine the blinking of the eye. The natural blinks of eye are distinguished from the unnatural blinks. The user has to blink his eye for a second if he wants to start moving or stop moving the wheelchair


Download full report
http://googleurl?sa=t&source=web&cd=1&ve...-1%2F2.pdf&ei=TmNCTsW8PIHsrAebz9muBw&usg=AFQjCNEJIR_QQ6HjJwHODbIupY5pZR3N-A&sig2=vJs6u46lDr0PLjoN9n_n2g