19 January 2016
The subject of Iris ageing - the effect of the passage of time on the recognition of individuals based on the analysis of their iris characteristics - is featured in the current edition of the international research journal IET Biometrics, with two rather different takes on the subject.
In response to the ongoing debate around iris ageing and to encourage productive and enlightening discussion, the IET Biometrics journal includes the following two key papers.
One of these contributions (written by Ortiz and Bowyer of the University of Notre Dame) is “A critical examination of the IREX VI results”, which reviews a report published originally by the US National Institute of Standards and Technology (NIST). The original NIST report looked at 3.5 million iris images from over 600,000 people collected in an operational system over a period of about six years and found no evidence of an iris aging trend. The Ortiz/Bowyer paper argues that improvements in the methodology used in the NIST report would lead to an uncovering of an ageing trend leading to a decrease in recognition rate over time.
The second paper (written by Grother and Matey, two authors of the original NIST report) is “IREX VI: mixed-effects longitudinal models for iris ageing”, which argues that “changes in recognition rates observed in the Notre Dame data are the result of lack of control of ambient conditions during …… collection and do not represent changes in the underlying iris pattern.” These contributions provide informed and well-argued position statements presenting different views of this issue, offering not only a broader perspective on the question of the effects of iris ageing, but providing a perspective which is relevant to the wider issue of template ageing in biometric systems.
This is an area of such importance and current debate that it is considered timely to make these two papers, together with a brief scene-setting Guest Editorial by Professor James Wayman, more generally available to the wider scientific community, as a means of furthering our understanding of this issue and encouraging better informed debate.
About the Editor-in-Chief
Michael Fairhurst is a Professor in the School of Engineering and Digital Arts at the University of Kent in the UK, where he was Head of Department for five years until 2008. His research interests focus on computational architectures and algorithms for image analysis and classification, and applications including handwritten text reading and document processing, medical image analysis and, especially, security and biometrics. He has published 350 papers in the scientific literature, and is an elected Fellow of the International Association for Pattern Recognition (IAPR) in recognition of his contributions to the field.
About the IET
The IET’s portfolio of research and letters journals and monographs (print and e-Book) are available online through the IET Digital Library together with conference proceedings, seminar digests and magazines. The IET Inspec database contains over 14 million abstract and indexing references to journal articles, conference proceedings and technical reports in the fields of science and technology, and IET.tv provides access to the world's largest specialised online archive of engineering and technology content.
For more information, visit www.theiet.org