A Novel Neural Eye Gaze Tracker
نویسندگان
چکیده
A gaze tracking system, based on a novel neural approach, is proposed. The work is part of a wider research project concerning the development of human computer interfaces (HCI) addressed to disabled people, that could overcome the drawbacks of most of the existing methods for gaze tracking that require either intrusive devices or expensive equipment. This work, instead, aims at developing a low cost, completely non-intrusive and selfcalibrating system which combines different techniques for three blocks in Eye Gaze Tracking, i.e. blink detection, feature extraction and neural computing. The experimental results show good accuracy in eye gaze tracking (rmse < 1 degree), and adequate generalization performance (rmse < 2 degrees).
منابع مشابه
Tracking Eyes and Monitoring Eye Gaze
In this paper, we present a non-intrusive eye tracker which can detect and track a user's eyes in real time as soon as the face appears in the view of the camera without special lighting or any marks on the user's face. We also discuss the problem of gaze monitoring. We employ neural networks to estimate a user's eye gaze using the images of user's both eyes as input to the neural networks. We ...
متن کاملNon-Intrusive Gaze Tracking Using Artificial Neural Networks
The goal of gaze tracking is to determine where a person is looking from the appearance of their eye. Numerous attempts have been made to create better gaze trackers. The interest in gaze tracking exists because of the vast number of potential applications. Two of the most common uses of a gaze tracker are as an alternative to the mouse as an input modality [Ware & Mikaelian, 1987] and as an an...
متن کاملIris Localisation for a Head-Mounted Eye Tracker
This paper discusses the image processing techniques needed to localise the iris outline in images of the eye produced by a novel, portable eye tracker. The tracker allows gaze direction to be measured by supplying simultaneous views of a subject's eye and of the world from a headmounted camera. Finding gaze direction relative to the head requires accurate and robust measurement of the iris out...
متن کاملWhat Are You Looking at? Improving Visual Gaze Estimation by Saliency
In this paper we present a novel mechanism to obtain enhanced gaze estimation for subjects looking at a scene or an image. The system makes use of prior knowledge about the scene (e.g. an image on a computer screen), to define a probability map of the scene the subject is gazing at, in order to find the most probable location. The proposed system helps in correcting the fixations which are erro...
متن کاملA Time Delay Neural Network model for simulating eye gaze data
Human eye movement modelling is a new, challenging, and promising research topic in computer vision. Human eye movement modelling aims at simulating the scan path in which a human being views an image, scene, or video. The successful modelling of human eye movements potentially benefits a wide range of applications such as image retrieval, image annotation, medical image diagnosis, and human vi...
متن کامل