DWT Based Feature Extraction for Iris Recognition

2 Abstract: This paper attempts to describe a unique approach to create an iris recognition system in which a mechanism that uses canny edge detection scheme and a circular Hough transform to determine the iris boundaries in the eye image which are used. Later two level discrete wavelet transform is applied to extract the patterns in a person's iris in the form of a feature vector. Matching is done using pair wise distance, which computes the Euclidean distance between two pairs of iris in data matrix. To conclude, our method has achieved a better total successive rate (TSR) and we have reduced equal error rate (EER),false accept rate (FAR) and false reject rate (FRR).