A New Snake Model for Pupil Localization Using Orthogonal Polynomials Transform

Abstract

 Abstract—In this paper a new approach for representing and evolving deformable contour or snake model to accurately detect pupil boundary for improving the performance of iris recognition systems is proposed. The proposed model extracts the boundary with computationally efficient Laplacian of Guassian (LoG) mask. The LoG mask is obtained from the set of polynomial basis operators derived from Orthogonal Polynomials Transform. Two types of controlling force models, introduced as internal and external forces are designed to properly activate the contour and locate it over the pupil boundary. The internal forces are designed to smooth the contour as well as to keep it close to a boundary by pushing the contour vertices towards the boundary of interest. The external forces are responsible for pulling the contour vertices towards the pupil boundary and the contour is deformed into a new shape in response to the effective force. A revised contour estimate of the selected boundary based on the execution of the contour tracing algorithm is generated. The results are highly encouraging to capture the contour of non-circular shaped pupil of iris. Experimental results on the CASIA v1.0 iris database demonstrate that the proposed snake model outperforms in both accuracy and speed.