Research On Iris-based Personal Verification Approaches

With the rapid development of information technology, information security becomes more and more important today. Some application domains need efficient automatic personal identification technology, such as Electron Commerce, Electron Bank, Network Security and so on. Biometrics gets more and more widely application in view of its stability, uniqueness and convenience. From the warranty of entrance to lock criminal in crowd, all are related to the market of application and trend of future of this technology.Biometrics combines the information technology with biology technology, which uses human inherent biological characteristics such as palm-print, iris, and face, and behavioral characteristics such as gait, signature and speech to confirm personal identity for replacing or strengthening the traditional personal identification approaches. Biometric technology is an up-and-coming biology technology and has been applied to feasible systems in the market. It regards its unique, reliable and stable physiological characteristics as the evidence of individual identity and applies the powerful computed ability of computer and technique of network to image processing and pattern recognition, then automated verify the individual identity.This paper describes a novel iris verification approach. Firstly, the iris image is pre-processed, which includes the localization of region of interest, normalization and enhancement of iris. The two segmented regions of interest are nearly not occluded by eyelash and eyelid. Then, wavelet moments method is used to extract the statistical features. Finally, in the verification stage, we adopt (Principle Component Analysis) PCA and one-to-one BP neural network structure to reduce the dimension of feature vector and verification. It can enhance the velocity of verification when partial iris is used for verification. The combination of PCA with BP guarantees the integrity of original data, avoids the superposition of original data, forms the new training samples and reduces the structure of BP neural network that can enhance the speed of study greatly.At the end of this paper, we present the prospect of iris verification for future work. The combination of biometrics and digital watermark is the novel technology of extensive applications, which is also the direction of future researches of this paper.