In iris recognition system, accurate iris segmentation and localisation from eye image is the foremost important step. In this project, a robust and efficient method of iris segmentation is proposed.
Iris recognition systems have widespread applications including their use as a security system at airports, banks, vault entrances, study of various effects on irises of twins, as a segmentation method in other applications, etc. Its purpose is real-time, high confidence recognition of a person's identity by mathematical analysis of the random patterns that are visible within the iris of an eye from some distance. Because the iris is a protected internal organ whose random texture is complex, unique, and very stable throughout life, it can serve as a kind of living passport or password that one need not remember but can always present.
Because the randomness of iris patterns has very high dimensionality, recognition decisions are made with confidence levels high enough to support rapid and reliable exhaustive searches through national-sized databases.
This project has been done by Aman Bindal, Akhil Goyal and Ankuj Gupta, students of the Computer Science Division, graduating in the year 2010.
This project has been shaped under the guidance of Prof. Anand Gupta, an esteemed Graphics lecturer in the Computer Science division.
Many algorithms have been suggested for segmenting of iris but most lack either of these features: speed, accuracy, bounding the iris with circle only, etc. This project aims at designing an algorithm to overcome these limitations.
The algorithm proposed by this project achieved speeds that were about ten times faster than the existing methods. Moreover, exact bounding of iris can be determined resulting in iris recognition systems that are more robust against fake-iris-based spoofing attempts. Furthermore, a high accuracy was achieved.
Their paper was published in the 2009 IEEE International Conference on Image Processing (ICIP) and in the 2009 International Journal of Critical Infrastructure Protection (IJCIP).
Aman Bindal can be contacted at This e-mail address is being protected from spambots. You need JavaScript enabled to view it
Student Activities 