Research Of Preprocessing And Feature Extraction Algorithms Of Iris Images

With the development of the biometric identification technology, many research institutions and companies pay attention to iris recognition technology because of its high stability and security.A iris recognition system consists of hardware and software. Hardware facilities is refers to the iris image intake equipment, software is the effective identification algorithm.This article study in improving the performance of the algorithm in the preprocessing, feature extraction and pattern matching of iris recognition technology.Use wiener filter to reduce the iris image noise in iris image preprocessing. Remove the influence of eyelash firstly with corrosion morphology method to ensure the accuracy of the follow-up positioning.Binary the eye image without eyelash to get the black pupil,then extract edge of it..Introduce the spiking neural networks which inherits the parallel mechanism from biological system to extract the outer edge of iris, use the fitting method based on effective arc.Normalize the preprocessed iris image to the rectangular area of fixed size with the double polar coordinates before texture feature extraction. Use histogram equalization to enhance important texture feature. Design a set of2D-Gabor filter with imaginary part only in12channels aim to extract feature in multiple perspectives.Finally in the pattern matching stage, using the new method based on relative distance of the key feature points.