%0 Conference Proceedings
%T A Feature-Based Gaze Estimation Algorithm for Natural Light Scenarios
%A Onur Ferhat
%A Arcadi Llanza
%A Fernando Vilariño
%B Pattern Recognition and Image Analysis, Proceedings of 7th Iberian Conference , ibPRIA 2015
%D 2015
%V 9117
%I Springer International Publishing
%@ 0302-9743
%@ 978-3-319-19389-2
%F Onur Ferhat2015
%O MV;SIAI
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2646), last updated on Thu, 12 May 2016 13:47:17 +0200
%X We present an eye tracking system that works with regular webcams. We base our work on open source CVC Eye Tracker [7] and we propose a number of improvements and a novel gaze estimation method. The new method uses features extracted from iris segmentation and it does not fall into the traditional categorization of appearance–based/model–based methods. Our experiments show that our approach reduces the gaze estimation errors by 34 % in the horizontal direction and by 12 % in the vertical direction compared to the baseline system.
%K Eye tracking
%K Gaze estimation
%K Natural light
%K Webcam
%U http://dx.doi.org/10.1007/978-3-319-19390-8_64
%P 569-576