In this paper we used a set of searching techniques that allow to gain information about eye movement, its location and point of view in real time. The algorithm determines the point on the monitor at which the user is looking at. To obtain such data it is necessary to determine the relative position of the eye and the head. The first step is the initialization during which a head model is created. After initialization, the tracking phase is started using an Active Appearance Models (AAM) and Pose from Orthography and Scaling with ITerations (POSIT) algorithm for head position estimation. The purpose of eye gaze estimation or eye tracking can be used for testing the effectiveness of the text, game, or advertising message. The aim of this work is to develop and implement a system for real time eye gaze estimation using PC's webcam only without any additional hardware.
展开▼
