john Gill technology header image

An Introduction to Biometrics - Iris Recognition

What is iris recognition?
The iris is the externally-visible, coloured ring around the pupil. It is a physical feature of a human being that can be measured and thus used for biometric verification or identification through the process of iris recognition. The human iris is well protected as although it is externally visible, it is an internal part of the eye. It is not genetically determined (which means that genetically identical eyes, e.g. the right and left eye of any given individual, have unrelated iris patterns) and it is believed to be stable throughout life (barring accidents and surgical operations). Iris patterns are both highly complex and unique (the chance of two irises being identical is estimated at 1 in 10 to the power of 78) [1] making them very well-suited for biometric identification.

How does it work?
An iris ‘scan’ is a high-quality photograph of the iris taken under near-infrared (near-IR) illumination [2]. Though visible light can also be used to illuminate the eye, darkly pigmented irises reveal more pattern complexity under near-IR light. Iris recognition systems generally use narrow-angle cameras and ask the user to position their eyes correctly in the camera’s field of view. The resulting photograph is analysed using algorithms to locate the iris and extract feature information, in order to create a biometric template or ‘IrisCode’.

  1. Acquire Sample
    The image of the iris is captured from a distance of 10-20cm (non-invasively) by a high-resolution camera which first focuses appropriately given the distance of the target, discounts reflections from glasses and acquires a digital photo of the iris.
    Variations in pupil size do not interfere with the randomness or uniqueness of iris patterns. Moreover, natural variations can be used as a means to confirm that the iris scanned is a real one. Other characteristics of the eye may render scanning difficult: for example the iris is often obscured by the eyelids (which may droop due to ageing or other factors), the eyelashes, lenses and eyeglasses. Furthermore, even in the absence of these obstacles, the whole process of acquiring an image of the iris for recognition purposes requires high-precision cameras since the iris is a relatively small (~1 cm), moving target, located behind a curved, wet, reflecting surface. Two more points to consider here are (a) using near infrared wavelength cameras as in this wavelength even dark brown coloured irises reveal their patterns well while with visible light cameras the result would have been dependent on the iris colour, and (b) user acceptance seems to be lower than with other biometrics as users feel a sense of discomfort during the enrolment process mainly due to the fact that it is not clear where to focus.
  2. Extracting Features
    The first task in feature extraction is to determine the location of the iris in the picture. This is done by localising the iris, pupil and both eyelid boundaries, excluding pupil and eyelashes from the photo and thus creating an iris mapping that is invariant to size, distance, magnification and pupil dilation. The next step involves creating the IrisCode (a high number – up to 2048 – of bit probabilities) through the use of proprietary algorithms which is ultimately stored in a template (256 bytes for the IrisCode itself + 256 bytes for masking bits). This then allows local or remote storing in centralised databases or portable media (smart cards). As will be explained later the template may contain less information (surprisingly up to 80% less) without significantly deteriorating the statistical process of the decision making.
  3. Comparing Templates
    Both verification (1:1) or identification (1:N) modes, involve taking a live photograph of the iris to be matched, and comparing the resultant IrisCode against the stored template (1:1 verification) or with N IrisCodes registered in a database (1:N identification). The matching is done through bit-to-bit comparison (logical exclusive OR operator) which is a very fast method of calculating the so-called average Hamming distance between the two IrisCodes compared [3]. There are other methods of measuring the correlations between two iris images but they are still under development.
  4. Declaring a match
    As is the case with all biometric systems, the matching process produces a score that is then forwarded to the decision process which compares the specific score to a decision threshold that may be adjusted to the application. In the case of iris recognition the threshold may be easily computed in such a way so as to allow 0 false matches almost independent of the number of entries in the database (in identification mode) and also ensuring minimal genuine false non-matches.

Some of the major applications of iris recognition currently are: immigration control/border crossing (using verification, identification or watch-lists), aviation security, controlling access to restricted areas/buildings/homes, database/login access. There is further scope for using this technology in other government programs (entitlements authorisation), automobile entry/ignition, forensic and police applications or any other transaction in which personal identification currently relies on passwords or secrets.

The largest deployment so far is currently in all 17 border entry points (air, land and sea ports) of the United Arab Emirates (UAE). Immigration Control checks all incoming passengers against an enrolled database of about 420,000 IrisCodes of persons who were expelled from the UAE (the captured IrisCode of an arriving passenger is matched exhaustively against every IrisCode enrolled in the database). After 3 years of operation and with an average 6,500 passengers entering every day - totalling 2.1 million passengers already checked - and some 9,500 identified as being on the list and travelling with forged identities, the system is described as very fast and effective [4].

The same system is also being trialled as a ‘positive’ application in Schiphol airport (NL), Frankfurt airport (DE), several Canadian and 10 UK airports during 2004. Furthermore, on the Pakistan Afghanistan border, the United Nations High Commission for Refugees (UNHCR) uses such a system for anonymous identification of returning Afghan refugees.


Published standards:

  • ANSI INCITS 379-2004: Information Technology-Iris Image Interchange Format
  • ISO/IEC 19794-6:2005: Information technology - Biometric data interchange formats - Part 6: Iris image data

Further information

[1] John Daugman, Univ. Cambridge, BIOSEC conference. Barcelona, June 2004.
[2] Near-IR wavelengths lie just beyond visible red light on the electromagnetic spectrum.
[3] Developed by J. Daugman: US Patent 4,641,349 held by IRIDIAN Technologies, Inc.
[4] John Daugman, Univ. Cambridge, I. Malhas, IrisGuard Inc. International Airport Review, issue 2, 2004.


The information contained in this section was collected from the following source:

Previous page
Next page


John Gill Technology Limited Footer
John Gill Technology Limited Footer