Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 47430 (05)
- University: Sharif University of Technology
- Department: Electrical Engineering
- Advisor(s): Babaie Zadeh, Massoud
- Abstract:
- About a century, “Eye Tracking” has been studied, and it has two definitions: • The process of measuring the point of gaze (where one is looking). • The process of measuring the motion of an eye relative to the head. Eye tracking technology has been used in many fields such as psychology. However, applications of this technology has been recently considered in marketing, computer interfacing, entertainment, training and so forth. Since pupil is a distinc area in eye images, pupil detection is one of the effective solutions of eye tracking. In most of the pupil detection approaches, the edge points of the pupil contour are detected firstly, and then the optimal ellipse is fitted to them. Occasionally, some data points which are not on the pupil contour are detected by mistake. In the process of ellipse fitting, these points accounts as outliers. In this Thesis, a new ellipse fitting method is proposed, which is robust to outliers and has better performance as compared to other algorithms. As gaze point detection depends on the accuracy of pupil detection results, ellipse fitting plays a great role in the gaze point estimation. One of the common applications of eye tracking is controling a computer systemto by using gaze points. Measurement noise and eye movements, which even exits at fixations, can reduce the accuracy of gaze point detection, and can make it hard to control the computer by means of the eyes. Therefore, the preprocessing of ”gaze signals” is a necessary stage. In the current thesis, different algorithms of eye movements mode detection and gaze point smoothing are studied. Eye movements mode detection algorithms usually force the user to set many thresholds manually whose their values are so effective on the accuracy of the whole process. Another novelty of this thesis, is proposing a new algorithm which can automatically detect fixation durations without needing to set manually any threshold and just by means of the descriptive statistics of the gaze signal data. The proposed method is related to eye movement mode detection, which is an essential step before gaze point smoothing
- Keywords:
- Outliers ; Gaze Tracking ; Eye Tracking ; Corneal Reflection ; Ellipse Fitting ; Gaze Point
Digital Object List
-
محتواي کتاب
- view
Bookmark