The Development of an Eye-Tracking System and Its Applications

• Main Authors: Kuo-Chun Chiu, 邱國鈞
• Other Authors: Mu-Chun Su
• Format: Others
• Language: zh-TW
• Published: 2006
• Online Access: http://ndltd.ncl.edu.tw/handle/rgqmp6

碩士 === 國立中央大學 === 資訊工程研究所 === 94 === Eye gaze tracking systems are systems that can estimate the gaze direction of a human user. Since eye gaze direction can express the interest of a user the applications of an eye gaze system are widely varied from human computer interaction and eye disease diagnosis to human cognition study. Therefore, eye gaze tracking has been a very attractive research topic in recent years. There are several different ways to track the directions of eye movements by refection of light and electrooculographic potential (EOG), etc. Each approach has its own advantages and disadvantages. For example, some systems are already commercially available; however, the costs of these systems usually are very expensive. On the other hand, some systems require attaching electrodes. Furthermore, some systems require the user to keep his or her head almost completely still; otherwise, a complex calibration process needs to be repeated again and again. In this thesis, a low cost eye gaze tracking system is proposed. With the eye gaze tracking system, people with severe disabilities can access computers via eye gaze. The system consists of two low-cost Web cameras. While the first Web camera surrounded by two infrared LEDs is attached to a headset which is worn on the user’s head the second Web camera is under the computer monitor. The images acquired by the first Web camera are used to compute eye gaze directions. An efficient gaze tracking algorithm has been developed to locate the center of pupil in images and then track the movements of the pupil. Then a simple but effective eye gaze mapping algorithm is used to compute eye gaze directions. The images acquired by the second Web camera are used to compensate head movements. Via the eye gaze tracking system and application software, people with severe disabilities, such as severe cerebral palsy or amyotrophic lateral sclerosis (ALS), can ask for helps, type texts, browse Internets, and control home appliances etc. Experimental results demonstrate the performance of the proposed system.