Robust Pose-Invariant Eye Gaze Estimation Using Geometrical Features of Iris and Pupil Images

Robust Pose-Invariant Eye Gaze Estimation Using Geometrical Features of Iris and Pupil Images

… Download …


Part of #Robust Pose-Invariant Eye Gaze Estimation Using Geometrical Features of Iris and Pupil Images# :

Publishing year : 2012

Conference : 20th Iranian Conference on Electrical Engineering

Number of pages : 6

Abstract: The Gaze Estimation problem, due to its manifold applications, including human computer interaction (HCI), especially for the handicapped, has been a topic of research since many years ago. Recently, non-intrusive methods, based on image processing, are more addressed, which are obtained by the development of the technology and can become more applicable. In this paper, we propose a non-intrusive algorithm for eye gaze estimation that works with video input from an inexpensivecamera and without special lighting. The main contribution of this paper is to propose a new geometric model for the eye region, which requires only an image of an iris for gaze estimation. Essential parameters for this system are the best fitted ellipse of iris andpupil center. A novel algorithm is also proposed to estimate the best fitted ellipse of iris which uses most of the iris boundary points and thus achieves high accuracy. Moreover, this algorithm, unlike the previous ones, poses from pre-assumptions on the head pose. All in all, the achievement of this paper is the robustness of the proposed system to the head poses variations. The performance of the method has been evaluated for both synthetic and real images leading to errors of 2.12 and 3.48 degrees, respectively