HUMAN EYE LOCALIZATION USING EDGE PROJECTIONS

Mehmet Türkan, Montse Pardàs, A. Enis Çetin

Abstract

In this paper, a human eye localization algorithm in images and video is presented for faces with frontal pose and upright orientation. A given face region is filtered by a high-pass filter of a wavelet transform. In this way, edges of the region are highlighted, and a caricature-like representation is obtained. After analyzing horizontal projections and profiles of edge regions in the high-pass filtered image, the candidate points for each eye are detected. All the candidate points are then classified using a support vector machine based classifier. Locations of each eye are estimated according to the most probable ones among the candidate points. It is experimentally observed that our eye localization method provides promising results for both image and video processing applications.

Download


Paper Citation


in Harvard Style

Türkan M., Pardàs M. and Enis Çetin A. (2007). HUMAN EYE LOCALIZATION USING EDGE PROJECTIONS . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, ISBN 978-972-8865-73-3, pages 410-415. DOI: 10.5220/0002055304100415


in Bibtex Style

@conference{visapp07,
author={Mehmet Türkan and Montse Pardàs and A. Enis Çetin},
title={HUMAN EYE LOCALIZATION USING EDGE PROJECTIONS},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,},
year={2007},
pages={410-415},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002055304100415},
isbn={978-972-8865-73-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,
TI - HUMAN EYE LOCALIZATION USING EDGE PROJECTIONS
SN - 978-972-8865-73-3
AU - Türkan M.
AU - Pardàs M.
AU - Enis Çetin A.
PY - 2007
SP - 410
EP - 415
DO - 10.5220/0002055304100415