Robust Iris Recognition in Unconstrained Environments

A biometric system provides the automatic identification of an individual based on a unique feature or characteristic possessed by him/her. Iris recognition (IR) is known to be the most reliable and accurate biometric identification system. The iris recognition system (IRS) consists of an automatic segmentation mechanism, which is based on the Hough transform (HT). The IRS is divided into six stages including imaging, pre-processing, segmentation, normalization, feature extraction and matching. Through this method, first, a photo is taken from the iris, and then edge detection is done. Later, on a contrast, adjustment is persecuted in the pre-processing stage. Circular HT is subsequently utilized for localizing circular area of the iris inner and outer boundaries. Also, through applying parabolic HT, boundaries are localized between the upper and lower eyelids. The proposed method, in comparison with the available IRSs, not only enjoys a higher accuracy, but also competes with them in terms of the processing time. Experimental results on the images available in the UBIRIS, BATH, CASIA, and MMUI databases show that the proposed method has an accuracy rate of 99.12%, 97, 98%, 98.80%, and 98.34%, respectively.