University of Tehran IRIS (UTIRIS) image repository is the first iris biometric databank registered in two distinct sessions of Visible Wavelength (VW) and Near InfraRed (NIR) imaging during 24-27th of June 2007. The database is constructed with 1540 images from 79 individuals from both right and left eyes demonstrated in 158 classes in total. The individuals are numbered the same in NIR and VW sessions. The Database is a copyright of Control and Intelligent Processing Centre of Excellence (CIPCE) at School of Electrical and Computer Engineering (ECE) in the University of Tehran.
Database Configuration
Visible Wavelength | NIR Wavelength | |
Image Dimension (Number of Pixels) | 2048 x 1360 | 1000 x 776 |
Compression Format | JPEG | BMP |
Camera Device | Canon EOS 10D | ISG Lightwise LW |
Color Space | RGB | Gray |
Color Profile | sRGB IEC61966-2.1 | |
Focal Length | 100 | |
Alpha Channel | No | |
Red Eye | Yes | |
F number | 2.8 | |
Exposure time | 1/60 |
Download Database
UTIRIS is compressed in “.zip” format and can be downloaded here
Authors
Citing UTIRIS
The description and preliminary results of UTIRIS analysis is outlined in:
[J] Mahdi S. Hosseini, Babak N. Araabi and H. Soltanian-Zadeh,”Pigment Melanin: Pattern for Iris Recognition,” IEEE Transactions on Instrumentation and Measurement, vol.59, no.4, pp.792-804, April 2010.
When referencing UTIRIS database, please cite the following:
@article{HosseiniAraabiSoltanianZadeh:2010,
author={Hosseini, M.S. and Araabi, B.N. and Soltanian-Zadeh, H.},
journal={Instrumentation and Measurement, IEEE Transactions on},
title={Pigment Melanin: Pattern for Iris Recognition},
year={2010},
month={april},
volume={59},
number={4},
pages={792 -804},
doi={10.1109/TIM.2009.2037996},
ISSN={0018-9456},
}
Hi, I found that quite a few images are not labelled consistently (as L/R) compared to the rest – is there an updated, corrected version of this very useful DB available?
Hi Sven,
Thanks for bringing this issue to my review. This is how the original data is taken. As you see there are some times more than 5 pictures per eye or less and unfortunately we do not have the matching pictures.
Thank you,
Mahdi S. Hosseini
Hi! You are was published very good dataset for iridology learners. Thank you, and let’s Hafez poetry is singing in your ears! =^.^=