A unified approach for unconstrained off-angle iris recognition

Improving the performance of non-idealistic iris recognition has recently become one of the main focus in iris biometric research. In real-world iris image acquisitions, it is common and unavoidable to capture off-angle iris images. Such off-angle iris images are categorized as non-idealistic because they substantially degrade the performance of iris recognition. In this paper, we present a unified framework designed to improve off-angle iris recognition performance. We propose combination of least square ellipse fitting (LSEF) technique and the geometric calibration (GC) technique for the iris segmentation. For off-angle images, the improper location of iris and pupil interferes with the ability to effectively segment the inner boundary and outer boundary of the iris image. With the proposed techniques, inner and outer boundaries are fitted iteratively. For feature extraction, we propose a NeuWave Network (inspired by the Haar wavelet decomposition and neural network). The iris features are represented using the wavelet coefficients. Each different angle of the iris have its own significant coefficient and these coefficient, with a set of weights, then forms the iris template. The approach is evaluated based on recognition accuracy measured by the false rejection, false acceptance rate, and decidability index. We evaluate the algorithms with WVU-IBIDC datasets.