Automatic gesture recognition for wheelchair control

In this work we propose an approach for controlling a wheel chair using Motion Capture, particularly gestures from the face are considered as commands for the basic control operations required for driving a wheelchair. Gesture recognition is carried out training an Artificial Neural Network, which is one of the most successful classifier in Pattern Recognition. Based on our experimentation, the proposed approach was able to detect gestures related to order commands which is useful for controlling a wheelchair by users with restricted mobility or disability in legs, arms or hands.