Description

ABSTRACT

Iris recognition has been paid more attentions due to its high reliability in personal identification recently. In this paper, an iris recognition system has been proposed. The steps of the proposed method include iris recognition, feature extraction and matching of the iris pattern. To describe the iris data DWT based features are used and for analyze purpose feature matching is employed. Experiments are performed using iris images obtained from  database. The method gives correct classification rate.

DEMO VIDEO

INTRODUCTION

Biometrics is automated methods of recognizing a person based on a physiological or behavioral characteristic. Compared with other biometric technologies, such as face, speech and finger recognition, iris recognition can easily be considered as the most reliable form of biometric technology. Iris is believed to allow very high accuracy, and there has been an explosion of interest in iris biometrics in recent years, because it has a good verification rate and resistance to imposter. Iris has some advantages over other biometrics. The iris is an externally visible and protected organ whose unique pattern remains stable throughout adult life. Iris data is non-identical for left, right eyes and for twins also. It can’t be borrowed, stolen, or forgotten, and forging one is practically impossible. Based on technology developed by Daugman, Iris scans have been used in United Kingdom at ATM’s instead of the normal codes to establishes the validity of a claimed identity by comparing a verification template to an enrollment template. Like other biometric systems, Iris recognition system has two modes: enrollment process and verification/identification process (say, matching process). In the enrollment process iris patterns are added to the database and in the matching process input iris pattern is compared with the stored patterns. The framework of iris recognition system is shown in Figure 1. Both enrollment and matching process include image acquisition, iris localization, iris normalization and feature extraction. In enrollment process, extracted feature vector is stored in the database. During the matching, the extracted feature is compared with stored features. In this paper, we have proposed an iris recognition system. The recognition system relies on four fundamental steps. The first step consists of iris localization using Circular Hough transform (CHT) . In the subsequent step, image is normalized into a fixed dimension. Then normalized image is decomposed by 2-D Haar wavelet and textural features are extracted.

EXISTING SYSTEM

In existing system we are used two types of techniques to approach the results. One is to extract the features of the image using DCT(Discrete Wavelet Transform) and for the classification of images we are using (SVM)Support Vector Machine algorithm. But with these types of techniques we are not capable to achieve the best results. That’s way we are proposing one new technology to get the performance accuracy.

PROPOSED METHOD

In proposed method we are going to use DWT(Discrete Wavelet Transform) and feature matching  algorithms to implement the results. The techniques which we are using in proposed method is advance than our existing techniques. In this project entire results we are going to achieve with a step by step process. The flow will start from the acquiring iris image  and to the recognition of iris to the database images. The hamming distance calculation also we are showing in the results.

BLOCK DIAGRAM

ADVANTAGES

• Extremely visible patterns from the distanced image
• Calculating the hamming distance will be useful

APPLICATIONS

• Bio metric identifications
• Security of national border application 

SOFTWARE REQUIREMENT

• MATLAB 2014 or above versions

Matlab code for Iris recognition