Face direction-based human-computer interface using image observation and EMG signal for the disabled

The paralytic caused by the high-level spinal cord injury needs a human-computer interface (HCI) for expressing their intention. In this paper, we propose a novel method to estimate face direction angle using both image observation and electromyogram (EMG) signal from neck muscles. The EMG signal to neck muscle is linear to the face direction angle, but it is undetectable in relatively small angle. Using the image observation, the small face angle is estimated by the geometric relationship between pupils and the face. If two measurements obtained by the EMG signal and the image observation are available, the face direction angle is estimated accurately by a linear interpolation method. We implemented a camera viewing direction control system using the face direction interface, and showed that the proposed method can be used to construct an HCI system for the disabled people with severe motor disabilities.