Robust Iris Recognition Based on Statistical Properties of Walsh Hadamard Transform Domain

In this paper, a new approach of iris image feature extraction technique based on the statistical properties of Walsh Hadamard Transform (WHT) domain is proposed. A Canny Edge Detection followed by Hough Transform is used to detect the iris boundaries in the digital image of an eye. The segmented and normalized iris region is divided into 8x8 non-overlapping blocks and WHT is applied to each block. Unique iris features are obtained by computing mean value of energy (MVE) and mean value of standard deviations (MSD) of WHT coefficients. The energy-compaction characteristics of WHT are used to capture iris texture variations. Fast Walsh Hadamard Transform Algorithm is used to reduce the computational time. The features extracted by the WHT domain are used to generate unique encoded binary image and corresponding unique binary bit stream/code is constructed. In order to reduce the size of the database, this binary bit stream instead of binary image is stored in database for matching purpose. Further to increase the security of the system, the bit stream obtained is first encrypted using the user key obtained from user password and then the encrypted bit pattern template is stored. Experimental results on Bath University Iris Database reveal that the proposed iris matching scheme provides results comparable to those of recent methods and is also computationally effective.