Title: Iris localisation and extraction algorithm from an eye image

Authors: Tomáš Fabián; Jan Gaura; Petr Kotas

Addresses: FEECS, Department of Computer Science, VŠB - Technical University of Ostrava, 17. listopadu 15, 708 33 Ostrava - Poruba, Czech Republic ' FEECS, Department of Computer Science, VŠB - Technical University of Ostrava, 17. listopadu 15, 708 33 Ostrava - Poruba, Czech Republic ' Department of Applied Mathematics, VŠB - Technical University of Ostrava, 17. listopadu 15, 708 33 Ostrava - Poruba, Czech Republic

Abstract: In this paper, we focus on common approaches in the area of eye and iris localisation. We describe in detail a new method for detecting iris in digital images. Our method is simple yet effective and estimation of the two circular boundaries is based on curve fitting and cost function maximisation. When we are searching for limbic boundary, we use the inverse gradient and star-like sampling scheme. Rather, an analytical approach is used during detection of pupillary boundary. We define the cost function reflecting the properties of brightness distribution in the pupil region. Our algorithm can be described in three simple steps; at first, we detect the bright point inside the pupil; at second, outer limbic boundary is found via statistical measurements of outer boundary points; and at third, inner boundary points are searched by means of defined cost function maximisation.

Keywords: iris extraction; iris segmentation; iris localisation; biometrics; eye images; digital images.

DOI: 10.1504/IJSISE.2012.047799

International Journal of Signal and Imaging Systems Engineering, 2012 Vol.5 No.2, pp.69 - 77

Published online: 31 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article