Development of EOG-Based Communication System Controlled by Eight-Directional Eye Movements

Abstract

A communication support interface controlled by eye movements and voluntary eye blink has been developed for disabled individuals with motor paralysis who cannot speak. Horizontal and vertical electro-oculograms were measured using two electrodes attached above and beside the dominant eye and referring to an earlobe electrode and amplified with AC-coupling in order to reduce the unnecessary drift. Eight directional cursor movements and one selected operation were realized by logically combining the two detected channel signals based on threshold setting specific to the individuals. As experimental results using a projected screen keyboard, processing speed was improved to 12.1 letters/min. while the accuracy was 90.4%

Online classification algorithm for eye-movement-based communication systems using two temporal EEG sensors

“…In this way, eye movements can be used as control signals for human-machine interfaces, allowing for interaction with the environment. This offers a potentially useful interface for disabled individuals [1][2][3][4][5][6][7][8][9][10][11][12].…”

A Naïve and Fast Human Computer Interface Controllable for the Inexperienced - a Performance Study

“…But the maximum bit rate would drop when higher accuracy is wanted through the reduction of options. The integration of the vertical eye movement can correct the problem, providing a second degree of freedom [6].…”

Low-cost system based on electro-oculography for communication of disabled people

“…Eye blinks, which last between 100 ms and 400 ms, cause high deflection in the vertical electrode potential around the eyes and are classified into two categories: the involuntary eye blink, which occurs frequently or is spontaneously induced by an external stimulus such as a flash of light, and the voluntary wink caused by intentional eye closing [3]. Intentional blinks are easily detected by their longer length and can be used as a complementary input to control the HCI [13].…”

“…To reduce long-term drifts, additional processing is necessary [3]. The systems must also be calibrated repeatedly for each individual.…”