A Novel Approach for Iris Recognition using DWT and PCA

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 PCA based iris recognition using DWT is proposed. The upper and lower portion of the iris which is occluded by the eyelids and eyelashes is removed using morphological process. According to Springer Analysis of CASIA data base, to get better recognition forty five pixels to left and right of the pupil boundary is considered as iris template for the proposed algorithm analysis. The image is enhanced using Histogram. Equalization to get high contrast. DWT is applied on histogram equalized iris template to get DWT coefficients. The features are extracted from the approximation band of the DWT coefficients using PCA. Multiple classifiers such as KNN, RF and SVM are used for matching. The proposed algorithm has better performance parameters compared to existing algorithm.