IRHDF: Iris Recognition using Hybrid Domain Features

Iris Biometric is a unique physiological noninvasive trait of human beings that remains stable over a person's life. In this paper, we propose an Iris Recognition using Hybrid Domain Features (IRHDF) as Dual Tree Complex Wavelet Transform (DTCWT) and Over Lapping Local Binary Pattern (OLBP). An eye is preprocessed to extract the complex wavelet features to obtain the Region of Interest (ROI) area from an iris. OLBP is further applied on ROI to generate features of magnitude coefficients. Resultant features are generated by fusion of DTCWT and OLBP using arithmetic addition. Euclidean Distance (ED) is used to match the test iris image with database iris features to recognize a person. We observe that the values of Equal Error Rate (EER) and Total Success Rate (TSR) are better than in [7].