ACADSTAFF UGM
| Judul/Title | AN IMPROVED PUPIL LOCALIZATION TECHNIQUE FOR REAL-TIME VIDEO-OCULOGRAPHY UNDER EXTREME EYELID OCCLUSION |
| Penulis/Author | Dr.Eng. Ir. Sunu Wibirama, S.T., M.Eng., IPM. (1) ; Dr.Eng. Ir. Igi Ardiyanto, S.T., M.Eng. (2); THORIQ SATRIYA (3); Teguh Bharata Adji, S.T., M.T., M.Eng., Ph.D (4); Ir. Noor Akhmad Setiawan, S.T., M.T., Ph.D., IPM. (5); Muhammad Taufiq Setiawan (6) |
| Tanggal/Date | 2019 |
| Kata Kunci/Keyword | |
| Abstrak/Abstract | Video-oculography (VOG) is a useful tool for detecting eye movement ab-normalities as well as for human-computer interaction. Performance of a real-time VOGsystem relies on how the center of pupil is estimated under various occlusions. However,the accuracy of the state-of-the-art algorithms decreases significantly with extreme eyelidocclusion, although they can estimate pupil center under different illumination conditionsand irregularity of pupil contour. To handle this problem, we propose a novel methodto localize pupil in a real-time VOG during extreme eyelid occlusion. We have improvedthe geometric ellipse fitting method by incorporating a cumulative histogram processingfor robust binarization and the random sample consensus (RANSAC) for removing out-liers. Experimental results with 90% eyelid occlusion show that the proposed algorithmincreases the accuracy of pupil localization up to 51% compared with a state-of-the-artmethod. During real-time pupil tracking, the proposed algorithm achieves significant ac-curacy improvement (N=9000 frames;p<.05) with less than 10 ms of computationaltime per frame. The proposed method shows promising results for accurate measurementof horizontal and vertical eye movements. |
| Rumpun Ilmu | Teknologi Informasi |
| Bahasa Asli/Original Language | English |
| Level | Internasional |
| Status |