Iris Localization and Extraction of Effective Region for Human IRIS Recognition
Eun-suk Cho, Yvette E. Gelogo, Seoksoo Kim · Proceedings of KIIT Summer Conference · 2011
The iris is so unique that no two irisis are alike, even among identical twins, in the entire human population. The human iris recently has attracted the attention of biometrics-based identification and verification research and development community. In this paper we propose a new biometric-based Iris localization and feature extraction system which is used to detect “IRIS Effective Region (IER)” and then extract features from “IRIS Effective Region (IER)” that are numerical characterization of the underlying biometrics. Using the high quality sensors, the system automatically acquires the biometric data in numerical format (Iris Images). The colored captured images will be processed to gray scale images. The new biometric-based Iris feature extraction will be compared to other two stored feature by producing a similarity score. This score will be indicating the degree of similarity between a pair of biometrics data under consideration. By considering Biological characteristics of IRIS Pattern we use Statistical Correlation Coefficient for this ‘IRIS Pattern’ recognition where Statistical Estimation Theory can play a big role. Depending on degree of similarity, individual can be identified.