• Lohith H
• Adarsh M C
• Balraju H N
• Soumya

Iris recognition system has become very important, especially in the field of security, because it provides high reliability. Because of its excellent dependability, the iris recognition system has become quite significant, particularly in security. Many academics have proposed novel approaches for improving the effectiveness of the iris recognition system. Various approaches for achieving excellent performance in iris recognition are presented in this thesis. Three feature extraction algorithms are employed to extract features from an iris image in the proposed system: Histogram of Oriented Gradient (HOG), Gray Level Co-Occurrence Matrix (GLCM), and Local Binary Pattern (LBP). In the classification stage, however, two classifiers are used: KNearest Neighbors (KNN) and Support Vector Machine (SVM). Before extracting features, the iris image goes through several stages: first, image resizing, which unifies all image sizes, second, segmentation, which determines the iris region in the eye image, and finally, normalization, which converts the iris region to a suitable shape with specific dimensions. The proposed methods have been tested on the UPOL and IITD iris databases. When the HOG+KNN approach was utilized, however, the proposed system had a 100% recognition rate.

Iris Recognition; Histogram of Oriented Gradient; Support Vector Machine; Biometric Authentication

"Secure Access to Bank Accounts at Cash Machines using Iris Recognition System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.d313-d322, May-2022, Available :http://www.jetir.org/papers/JETIR2205458.pdf

"Secure Access to Bank Accounts at Cash Machines using Iris Recognition System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppd313-d322, May-2022, Available at : http://www.jetir.org/papers/JETIR2205458.pdf