| Monozygotic / Non-monozygotic (MZ/NMZ) Iris Dataset |
It contains 1,615 iris images organized as 11,907 monozygotic pairs (images of different irises of same individual) and 11,907 non-monozygotic pairs (images of irises of unrelated persons). |
2025 |
Access Link |
Cite |
University of Notre Dame |
| ND-NBSI-2025 Dataset |
The ND-NBSI-2025 Dataset consists of 1,000 iris images synthesized by a model trained to mimic near-infrared iris images captured from infants. |
2025 |
Access Link |
Cite |
University of Notre Dame |
| Synthetic Forensic Iris (UND-SFI-2024) Dataset |
The data is categorized into 18 disjoint ranges of PMI (Post-Mortem Interval). In each range, there are 10,000 images representing 1,000 non-existent identities. |
2024 |
Access Link |
Cite |
Department of Computer Science and Engineering, University of Notre Dame |
| Iris Super Resolution Dataset |
It contains 4,320 color iris images from 704 subjects (392 females and 312 males), with three images per eye per subject. |
2023 |
Access Link |
Cite |
Computer Vision and Biometric Laboratory (CVBL), Islamic Azad University, Isfahan |
| LivDet-Iris-2023-Part1 |
It contains images of live (authentic) irises and images of irises synthetically-generated by deep learning-based generative adversarial networks. |
2023 |
Access Link |
Cite |
University of Notre Dame |
| SBVPI |
Full dataset includes 16,717 RGB images. |
2023 |
Access Link |
Cite |
University of Ljubljana |
| I-SOCIAL-DB |
This dataset is composed of 3,286 ocular regions, extracted from 1643 high resolution face images of 400 individuals. |
2021 |
Access Link |
Cite |
Department of Computer Science, Università degli Studi di Milano, |
| The Hong Kong Polytechnic University Cross-Spectral Iris Images Database |
This database consists of total 12,540 iris images (209 ´ 2 ´ 2 ´ 15) which are acquired with 15 instances from 209 different subjects. |
2017 |
Access Link |
Cite |
The Hong Kong Polytechnic University |
| ND-Iris-0405 Dataset |
It contains 64,980 iris images from 356 subjects (712 unique irises). |
2016 |
Access Link |
Cite |
University of Notre Dame |
| LivDet-Iris 2013 (Warsaw Subset) |
It comprises 852 images of authentic eyes and 815 images of paper printouts used for presentation attacks. |
2013 |
Access Link |
Cite |
Warsaw University of Technology |
| UBIPr |
The UBIPr dataset is a version of the UBIRIS.v2 set, with images cropped in a way that they cover wider parts of the ocular region than the original UBIRIS.v2 data. |
2012 |
Access Link |
Cite |
University of Beira Interior |
| CASIA-IrisV3 |
The CASIA-Iris V3 dataset comprises 22,034 iris images with a resolution of 640*480 pixels. |
2011 |
Access Link |
Cite |
CASIA |
| CASIA-IrisV4 |
It includes 54,601 images from 2,800 subjects distributed across six subsets: Interval, Lamp, Twins, Distance, Thousand, and Syn. |
2011 |
Access Link |
Cite |
CASIA |
| IIT Delhi Iris Database (Version 1.0) |
It contains images captured in a controlled indoor environment and has been widely used for developing and testing iris recognition algorithms. |
2010 |
Access Link |
Cite |
IIT Delhi |
| UBIRIS v2 |
It offers over 11,000 images captured at a distance (between four and eight meters) and on-the-move. |
2010 |
Access Link |
Cite |
University of Beira |
| MMU-v1 |
It consists of 450 images obtained from 45 subjects. |
2010 |
Access Link |
None |
Multimedia University (MMU) |
| ND-Iris-0405 |
It contains 64,980 iris images obtained from 356 subjects (712 unique irises) between January 2004 and May 2005. |
2009 |
Access Link |
Cite |
The University of Notre Dame du Lac |
| UBIRIS v1 |
This dataset provides 1,877 images acquired under less constrained imaging conditions. |
2005 |
Access Link |
Cite |
University of Beira |
| CASIA-IrisV2 |
It contains 2,400 images from 120 individuals, captured at a VGA resolution (640×480). |
2004 |
Access Link |
Cite |
CASIA |
| CASIA-IrisV1 |
It contains 756 images from 108 subjects, captured at a resolution of 320×280. |
2003 |
Access Link |
Cite |
CASIA |