| Paper ID | D-1-2.6 |
| Paper Title |
Fixational Feature-Based Gaze Pattern Recognition using Long Short-Term Memory |
| Authors |
Suparat Yeamkuan, Kosin Chamnongthai, King Mongkut’s University of Technology Thonburi, Thailand |
| Session |
D-1-2: Machine Learning Techniques for Image & Video |
| Time | Tuesday, 08 December, 15:30 - 17:00 |
| Presentation Time: | Tuesday, 08 December, 16:45 - 17:00 Check your Time Zone |
|
All times are in New Zealand Time (UTC +13) |
| Topic |
Image, Video, and Multimedia (IVM): |
| Abstract |
The pattern of eye gaze is increasingly powerful for human-computer interaction tasks. Understanding of gaze pattern can provide valuable information regarding to users’ attention. Certainly, the patterns of eye gaze known as eye accessing cues are related to the cognitive processes of the human brain. In this paper we propose a method for gaze patterns recognition, where a gaze data was collected from eye tracker. Consequently, a gaze fixation feature and Long Short-Term Memory technique is employed in this work for the recognition. To evaluate the performance of the proposed method, we have an experiment with 7 examiners, in which they have to looked at 3 tasks of point, rotate and slide on screen. The experimental results show the proposed method offering favorable performance on a standard eye tracker, respectively. |