One machine can do the work of fifty ordinary men.  No machine can do the work of one extraordinary man.  ~Elbert Hubbard

The Working of an Iris Recognition SystemShounak Acharya, Amitabh Banerjee(4th yr- IT)

Overview
A biometric system provides automatic recognition of an individual based on some sort of unique feature or characteristic possessed by the individual. Biometric systems have been developed based on fingerprints, facial features, voice, hand geometry, handwriting, the retina, and the one presented here, is the iris. The iris is a thin circular diaphragm, which lies between the cornea and the lens of the human eye. The iris is perforated close to its centre by a circular aperture known as the pupil. The function of the iris is to control the amount of light entering through the pupil, and this is done by the sphincter and the dilator muscles, which adjust the size of the pupil. The average diameter of the iris is 12 mm, and the pupil size can vary from 10% to 80% of the iris diameter. The iris consists of a number of layers; the lowest is the epithelium layer, which contains dense pigmentation cells. The stromal layer lies above the epithelium layer, and contains blood vessels, pigment cells and the two iris muscles. The density of stromal pigmentation determines the colour of the iris. The externally visible surface of the multi-layered iris contains two zones, which often differ in colour. An outer ciliary’s zone and an inner pupillary zone, and these two zones are divided by the collarette – which appears as a zigzag pattern.
Formation of the iris begins during the third month of embryonic life. The unique pattern on the surface of the iris is formed during the first year of life, and pigmentation of the stroma takes place for the first few years.
Formation of the unique patterns of the iris is random and not related to any genetic factors. The only characteristic that is dependent on genetics is the pigmentation of the iris, which determines its colour. Due to the epigenetic nature of iris patterns, the two eyes of an individual contain completely
independent iris patterns, and identical twins possess uncorrelated iris patterns.

e1

Introduction
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. Image processing techniques can be employed to extract the unique iris pattern from a digitized image of the eye, and encode it into a biometric template, which can be stored in a database. This biometric template contains an objective mathematical representation of the unique information stored in the iris, and allows comparisons to be made between templates. When a subject wishes to be identified by iris recognition system, their eye is first photographed, and then a template created for their iris region. This template is then compared with the other templates stored in a database until either a matching template is found and the subject is identified, or no match is found and the subject remains unidentified.

Working of the System
The Working of the system can be categorized into steps according to the following algorithm

e2

Image Capture: Capturing the image for applying the recognition algorithm is the most important part in this the recognition algorithm. The images are taken in Near Infrared Regions (NIR) spectrum of the electromagnetic waves so as to store the images in black and white i.e., gray scale images are stored. This not only reduces the storage in terms of reducing the RGB information to be stored per pixel, but also

  1. speeds up the computation time as only single intensity values are considered per pixel instead of three (RGB). Also NIR image capture reduces the noise due reflections occurring from the eye.

  2. Iris Segmentation: Iris Segmentation is the most difficult step in the Iris Recognition procedure. This not only segments out the iris from the pupil and the cornea, but it also removes the noise due to the occluding eyelashes. There are basically two methods employed in iris segmentation- John Daugmann’s Integro differential operator and the Circular and the Linear Hough transform. In our project we implemented the Circular Hough Transform which consists of creating an edge map of the eye image. Then on each point of the edge map two circles-one with the radius of the iris and one with radius of the pupil are drawn. By drawing I mean that in an accumulator array which is the image array (initialized to zero), each pixel position’s value is incremented if the radius passes through that pixel with centre at different edge-map pixels. Then the pixel whose accumulator value is maximum at the end of the pass with iris radius is considered as the iris centre and the pixel with maximum accumulator value with pupil radius is considered as the pupil’s centre.

e3
e4
Segmented eye image

Normalization: This step converts the segmented eye image into a consistent form on which the recognition procedure can be applied. And which is invariable to size shape and rotation of the eye. This is implemented by the

  1. Daugmann’s Rubber sheet model which converts the Donut shaped iris into a rectangle

e5
Original Eye Image                                     Normalized image

  1. Feature Encoding: In this step the eye image obtained in the above step is convolved with the 1-D Log Gabor filters. Gabor filters are basically used as part of wavelet analysis which is based on the principal of dividing themselves into small portions, convolving with them, and scaling itself to cover a larger area of the image. This typically creates a 9600 bit pattern for a 280X480 image which is known as the iris template. Each image captured, is converted first into this before any matching is done. Also the eye images are stored in the form of these templates in the databases. All comparisons are done on these templates only.

  2. Pattern Matching: The bit pattern calculated in the above step is matched with a template stored in the database by calculating the hamming distance. If the Hamming distance is greater than a specified threshold (Typically 0.32) then the image is rejected else accepted.

Conclusion
The method presented above is the most authentic biometric system ever developed. It has a false matching rate of only 1.98% making it the most secure authentication system. It is already in use in many real-time systems for physical verification of employees, airport check-ins etc. Nokia is also planning to launch Iris Recognized mobiles by the end of March 2008. Thus Iris Recognition has the potential for replacing all password authenticated systems.