Iris Feature Matching Research Articles

A Selective Feature Matching Approach for Iris Recognition

Reliable automatic recognition of persons has long been an attractive goal of many researchers. Thus the recognition of an individual based on iris pattern is gaining more popularity due to the uniqueness of the pattern among the people which are highly stable starting from about one year past the date of birth, until death. The probability for the existence of two irises that are same has been theoretically estimated to be very high, i.e. one in 10 which counts for the unique characterization of the iris. Although many approaches for iris recognition have been proposed by many researchers in the last few years, in this paper a selective iris feature matching method for iris recognition based on optimized wavelet decomposition of normalized iris image has been proposed. Comparing the average normalised correlation of the wavelet coefficients of optimised level and its adjacent levels improved matching is obtained, thus performing uniqueness verification of a person. General Terms Pattern Recognition and Analysis, Security, Proposed Matching Algorithm, Reliable Person Authentication

PRIVACY PRESERVING IRIS BASED BIOMETRIC IDENTITY VERIFICATION / IŠSAUGANTIS PRIVATUMĄ, AKIES RAINELĖS ANALIZE GRĮSTAS, BIOMETRINIO TAPATUMO VERIFIKAVIMAS

Iris biometrics is considered one of the most accurate and robust methods of identity verification. Individually unique iris features can be presented in a compact binary form easily compared with reference template to confirm identity. However, when templates or features are disclosed, iris biometrics is no longer suitable for verification. Therefore, there is a need to perform iris feature matching without revealing the features itself and reference template. The paper proposes an extension of the standard iris-based verification protocol that introduces features and a template locking mechanism, which guarantees that no sensitive information is exposed.

The relative distance of key point based iris recognition

Iris recognition has received increasing attention in recent years as a reliable approach to human identification. This paper makes an attempt to analyze the local feature structure of iris texture information based on the relative distance of key points. When preprocessed, the annular iris is normalized into a rectangular block. Multi-channel 2-D Gabor filters are used to capture the iris texture. In every filtered sub-image, we extract the points that can represent the local texture most effectively in each channel. The barycenter of these points in each channel is called the key point and a group of key points are obtained. Then, the distance between the center of key points of each sub-image and every key point is called relative distance, which is regarded as the iris feature vector. Iris feature matching is based on the Euclidean distance. Experimental results on public and private databases show that the performance of the proposed method is encouraging.