IREMD: An Efficient Algorithm for Iris Recognition

The iris pattern is an important biological feature of human body. The recognition of an individual based on iris pattern is gaining more popularity due to the uniqueness of the pattern among the people. In this paper, the iris images are read from the database and preprocessing is performed to enhance the quality of images. Further the iris and pupil boundaries are detected using circular Hough transform and normalization is performed by using Dougman's rubber sheet model. The fusion is performed in patch level. For performing fusion, the image is converted in to 3x3 patches for mask image and converted rubber sheet model. Patch conversion is done by sliding window technique. So that local information for individual pixels can be extracted. The desired features are extracted by block based empirical mode decomposition as a low pass filter to analyze iris images. Finally the matching between the database image and test image is performed using Euclidean Distance classifier. The experimental results shows 100% accuracy on CASIA V1.0 database compared with other state-of-art methods.