Abstract
Abstract This paper proposes a novel algorithm for the automatic classification of iris images using a 2_D (two Dimension) Variation to estimate the fractal dimensions of the iris. The new technique divided in to three main step. In the first step the segmentation process in iris recognition is used to localize the circular iris and pupil regions, excluding eyelids and eyelashes. The extracted iris region is normalized into a squares block with constant dimensions. In the second step, the feature extraction techniques are improved and implemented. A new feature extraction technique based on a 2_D Variation to estimate the fractal dimensions is used. Finally The Normalized Correlation is used to classify the iris features. The techniques performed with perfect segmentation on a set of 995 iris images of greyscale eye images from MMU database. The as False Accept Rate (FAR) and False Reject Rate (FRR) and (RR) recognition rate are calculated for this technique. The results of the algorithm proved that. The a 2D (two Dimension) Variation to estimate the fractal dimensions method it is a good feature extraction technique. It gives FAR=(1.02) and FRR= (0.52) and a high recognition rate is 98.45%..