A fast accurate algorithm for iris localization using a coarse-to-fine approach

Iris-based biometric system is gaining its importance in different applications such as controlling access to restricted areas and database access and login. The first step in this system is to localize the iris part. As the localization result becomes more accurate, a high performance of feature extraction and recognition is obtained. Traditional iris localization methods often involve an exhaustive search of a three-dimensional parameter space, which is a time consuming process. This paper presents a coarse-to-fine approach to address the computational cost problem with an acceptable accuracy. The iris gray image is transformed to a binary image using an adaptive threshold obtained from analyzing the image intensity histogram. Morphological processing is then used to extract an initial center point, which is considered as the initial center for both pupil and iris boundaries. Finally, a refinement step is made using an integrodifferential operator to get the final iris and pupil centers and radii. This system proves to be robust against occlusions and intensity variations.