Gusti Pangestu, Fitri Utaminingrum, Fitra A. Bachtiar
Eye movement detection is one of the most developed technology, especially in human and computer interaction. Many research is developed by using this technology such as lying detection, security using captcha of movement eye until fatigue detection. Eye movement detection also applied for controlling an electronic device like a wheelchair. Eye movement can furnish an easy input source by tracking user point of view and applied it as guided. In general, the process of tracking eyeball movement required a face detection first and also detect an eye area. Unlike the face and eye detection method, eye movement detection still needs a lot of improvement. In this paper, we use multiple approaches to detect eyeball movement by included corner triangle similarity methods, face landmark methods, and Naïve Bayes classifier. This proposed approach is able to handle many various directions of movement of the eye and produce an accuracy of detection about 85%. This multiple approaches also can be proposed as an alternative option to detect the eyeball movement. © 2019 International Center for Scientific Research and Studies.
Computer Vision Research Group, Faculty of Computer Science, Brawijaya University, Malang, Indonesia; Intelligent System Research Group, Faculty of Computer Science, Brawijaya University, Malang, Indonesia
