ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

IRIS RECOGNITION USING HOUGH’S TRANSFORM GAMMA CORRECTION AND HISTOGRAM THRESHOLDING METHOD

Journal: International Journal of Engineering Sciences & Research Technology (IJESRT) (Vol.5, No. 10)

Publication Date:

Authors : ; ; ;

Page : 84-92

Keywords : Iris Recognition; Biometrics; Iris Segmentation; Gamma correction; Histogram Thresholding; Growing based segmentation; Gabor filter; Matching; Norm alization; and Image Processing .;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

In biometric identification, the Iris recognition system is a most popular research field in recent years. Due to iris biometric recognition reliability and nearly perfect recognition rates, used in high security areas. An Iris recognition system is designed in order to verify both the uniqueness of the human iris and performance as a biometric identification. This Iris recognition system consi sts of an automatic segmentation system that is based on the Hough Transform Gamma Correction and Histogram Thresholding method and is able to localize the circular Iris and pupil region, reflection, occluding eyelid and eyelashes. In this paper, we will d iscuss the different steps to recognize an Iris image which mainly include acquisition, segmentation, normalization, feature extraction and matching. We overcome the user's cooperation constraints in the biometric Iris recognition. However, it is highly pr obable that images captured at a distance, without user's cooperation and within highly dynamic capturing environments lead to the appearance of extremely heterogeneous images, with several other types of information in the captured Iris regions (e.g. iris obstructions by eyelids or eyelashes and reflections). The algorithm is implemented over CASIA v4.0 database, IIT Delhi Database and ICE 2005 database and the accuracy of 99.08%, 99.86% and 98.17% is achieved respectively which is seen better from other l iterature studied and cited in the work.. The experimental results provide significant improvement in the segmentation accuracy.

Last modified: 2016-10-05 19:28:37