Eye State Recognition Using Multiple Methods for Applied to Control Smart Wheelchair

Abstract

People with multi-disability order need more handling than normal people. Smart wheelchair also developed with conventional mechanism that has more improvement in any aspect such as automatic system until control system. We develop a way for controlling smart wheelchair with movement of eyelid. In other ways, our system have capability to recognize state of the eye whether the eyes in opened or closed state. Opened and closed state in the eye can made a benchmark to control a wheelchair. In our research, we develop a system to recognize whether eye in the opened or closed state by using Multiple Method consisting of Haar cascade to detect eye location, Vertical Image Projection (VIP) to extract the feature and Learning Vector Quantization (LVQ) Neural Networks to recognize state of the eye. Our method produce an accuracy until 90.32% to recognize eye state. This approach can be used as an alternate way to control movement such go forward or stop by using their eyelid movement in smart wheelchair for disabled people.

Development of an Autonomous Driving Smart Wheelchair for the Physically Weak

“…For example, some studies have used gaze and voice recognition to control electric wheelchairs. Gusti et al developed a method for controlling smart wheelchairs using eyelid movements [5], and Nikunj et al developed a system that enables a person to travel alone by providing freedom of wheelchair operation through voice commands [6]. Kumar et al also applied a voice recognition module in an electric wheelchair and developed a wheelchair with a voice recognition system that enabled the standing position to be achieved [7].…”

Control Systems and Electronic Instrumentation Applied to Autonomy in Wheelchair Mobility: The State of the Art

“…A proof of concept was carried out by verifying the movement of the chair with the movement of the eyeball. A control based on eye movement is designed by Pangestu et al [29] A neural network is implemented to learn to recognise the state or characteristics of the eye based on a bank of photos of eyes in different open and closed positions. The Viola-Jones algorithm for face and eye detection is implemented.…”

“…[52,56,58,61] have a higher computational cost, due to the implementation of algorithms and neural networks, but the controllers based on thresholds present in the MEMS category have a lower computational cost. The computational expense in controllers which involve sEMG and EOG was higher in articles [29,69,72]. The rest of the controllers involve thresholds for the control and use of PID controllers.…”