To Study and Implement Iris Recognition to Give Firsthand Experience to An Alternative Approach to Government of India for AADHAR CARD to be Implemented by Unique Identification Authority of India (UIDAI)

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. Most commercial iris recognition systems use patented algorithms developed by Daugman, and these algorithms are able to produce perfect recognition rates. However, published results have usually been produced under favourable conditions, and there have been no independent trials of the technology. The objective of present work is a self-memorandum which revolves around “To Study and Implement Iris Recognition to Give First-hand Experience to An Alternative Approach to Government of India for ‘AADHAR CARD’ to be Implemented by Unique Identification Authority of India (UIDAI)”. The alternative approach is based on the premise that as existing work are patented and need to search the iris boundaries over large parameter space exhaustively, which takes more computational time. Moreover, they may result in circle detection failure, because some chosen threshold values used for edge detection cause critical edge points being removed. In this work, we implement simple method for iris recognition in iris images to implement in day to day life, using MATLAB^®. The emphasis will be only on the software for performing recognition, and not hardware for capturing an eye image. Every biometric system has mainly two modules, one is ‘verification’ and the other is ‘recognition’. The verification part is involved in matching the test/real-time input with current database while recognition involves presenting the output from the database to which the test/real-time input. The work presented in this thesis involved developing an ‘open-source’ iris verification system. Gibson always stressed that one must understand the nature of the environment before one can understand the nature of visual processing. However, his comments have gone largely unheeded in the mainstream of vision research. There seems to be a belief that images from the natural environment vary so widely from scene to scene that a general description would be impossible. Thus an analysis of such images is presumed to give little insight into visual function. As our goal is to study and implement the iris recognition technology with an alternative approach. Our alternative approach implemented the algorithm in MATLAB^® code, is based on two assumed premises: The intensity of brightness of sclera is greater than iris, whose intensity of brightness is in turn greater than pupil. Iris and pupil are concentric. The iris recognition system consists of an automatic segmentation system that is based on the Hough transform, and is able to localise the circular iris and pupil region, occluding eyelids and eyelashes, and reflections. The extracted iris region was then normalised into a rectangular block with constant dimensions to account for imaging inconsistencies. Finally, the phase data from 2D Log-Gabor filters was extracted and quantised to four levels to encode the unique pattern of the iris into a bit-wise biometric template. The Hamming distance was employed for classification of iris templates, and two templates were found to match if a test of statistical independence was failed. Iris verification is shown to be a reliable and accurate biometric technology.