21-08-2012, 10:59 AM
AN EMBEDDED SYSTEM FOR IRIS RECOGNITION
IRIS SEMINAR.pptx (Size: 1.15 MB / Downloads: 39)
ABSTRACT
A biometric system provides automatic identification of an individual based on a unique feature or characteristic possessed by the individual. Iris recognition is regarded as the most reliable and accurate biometric identification system available. The present approach is authentication based on iris texture analysis. A HW/SW implementation algorithm for detection and localization of iris based on shape properties are described. The designed system has been implemented in a CYCLONE II DE2 Board using the NIOS processor. The data base CASIA version 1.0 is used for the test.
CONTENTS
Introduction
Methodology
Hardware Implementation
Experimental results
Advantages and disadvantages
Conclusion
References
INTRODUCTION
Biometrics: The method of identifying a person based on biological, morphological or behavioral characteristic. Biometric techniques are classified into 3 categories: biological, behavioral and morphological.
Iris Biometric authentication: The iris is an externally visible, yet protected organ whose unique epigenetic pattern remains stable throughout adult life. These characteristics make it very attractive for use as a biometric for identifying individuals. Hence it is accepted as one of the most efficient biometric method.
METHODOLOGY
The proposed algorithm involves three main modules:
Iris Localization
Extraction of code
Template Matching
Iris localization involves following steps:
Firstly an average filter is applied to the image in order to reduce noise.
The image is now converted into grey scale to remove the illumination effect.
Pupil detection: Pupil is detected using circular Hough transform, the equation of circle is (x-a)2 + (y-b)2 = r2 After transformation into parameter space it is represented as x = a + r cos (θ) and y= a - r sin (θ)