Accessible Human-Computer Interaction Based On EOG

Accessible technology enabled people with disabilities to fully participate and contribute to society. Human-Computer Interaction has become an important area of research and development for the disabled. If we can design a HCI system which is using impression of the user to control other applications, it will bring them great conveniences. An eye movement-controlled accessible HCI which can be used for the disabled who have motor paralysis and who cannot speak in multiple applications (such as communication aid and smart home applications) is described here.EOG(electro-oculography) signal can be used for recognizing the directions of eye movements or voluntary eye blinks and it can be used in Human-Machine Interface fields. But the original signal contains baseline drift cased by muscle movement and involuntary eye blinks, and may cause a great deal of difficulties in signal recognition. In this paper, a mathematical morphology based algorithm is presented to process the EOG signals. This new approach can reduce the artifacts effectively and recognize the directions of eye movements and voluntary eye blinks using a set of thresholds.Our work is to realize a HCI system which included both software and hardware. This system consists of four major parts: (1) signal acquired module, (2) signal processing module, (3) a ZigBee wireless module, and (4) application interface. Horizontal and vertical Electro-Oculography (EOG) signals are measured using five surface electrodes placed on the head .The vertical electrodes are placed about 1.0 cm above the right eyebrow and 2.0 cm below the lower lid of the right eye, the horizontal electrodes are placed 2.0 cm lateral to the each side of outer canthi and the last electrode is placed on user's forehead to serve as a ground. The two-channel amplifier is comprised of instrumentation amplifiers, band-pass filters and shift circuits. The EOG signals are sampled at the rate of 250Hz and then sent to signal processing module which is based on the method of mathematical morphology to recognize the direction of eye movements and voluntary eye blink. And finally, a HCI system for disabled by this method has been designed and used in ICU and many other fields. The experiments show that the average correct rate is 96.2 % and the bit rate is above 169.4 bit/min with this system and it can be employed in Human-Computer Interface fields. And we have developed a series of applications of this system.