Title: Improvement in Eye Glance Input Interface Using OpenCV

Year of Publication: Jul - 2015
Page Numbers: 207-211
Authors: Kota Akehi, Shogo Matuno, Naoaki Itakura, Tota Mizuno and Kazuyuki Mito
Conference Name: The International Conference on Electronics and Software Science (ICESS2015)
- Japan

Abstract:


In this study, we developed an eye glance input interface using a camera to capture eye gaze input. Our previous studies[1][2] involved the development of an eye control input interface using an electro-oculograph (EOG) amplified by AC coupling. Our proposed eye gesture input interface used a combination of eye movements and did not require the restriction of head movement, unlike conventional methods. However, this method required an input start operation before capturing could commence. This led us to propose an eye glance input method that uses a combination of contra-directional eye movements as the input and avoids the need for start operations. The eye gesture input method required the use of electrodes, which were uncomfortable to attach. The interface was changed to a camera, which used facial pictures to record eye movements, and an improved noncontact and low-restraint interface. The eye glance input method measures the directional movement and the time required by the eye to move a specified distance using the optical flow with OpenCV from Intel. We analyze the waveform obtained from eye movements using a purpose-built detection algorithm. In addition, we examine the reasons for detecting a waveform when eye movements are not captured correctly.