CASIA-IrisV4 Iris Image Database
Six near-infrared or synthetic iris subsets spanning close-range, lamp variation, twins, distance, large-scale, and synthetic recognition.
At a glance
| Field | Value |
|---|---|
| Short name | casia_iris_v4 |
| Full name | CASIA-IrisV4 Iris Image Database |
| First published | Unknown |
| Publication date precision | Unknown |
| Publication date evidence | Unknown |
| Publication date source field | Unknown |
| Publication date reviewed | Unknown |
| Primary category | iris_biometrics |
| Resource role | current_dataset |
| Dataset family | casia_iris_v4 |
| Contained modalities | iris_biometrics |
| Tasks | biometric_recognition, classification |
| Primary reported quantity | 54,601 images |
| Classes | Not reported (Not reported) |
| Splits | all |
| Size | 1.86 GB |
| Source-stated terms | Public domain; source access terms apply |
| Normalized terms | cc0 |
| Descriptive screening label | Standard label without an explicit NC clause; not a permission finding |
| Terms scope | unknown |
| Access friction | anonymous_direct |
| Route backend | Manual (upstream-gated) |
| Availability | available (checked 2026-07-21) |
| Acquisition support | guided_instructions_only |
| Legacy sample-loader status | Metadata and access only |
Reported quantities
| Role | Count | Unit | Scope | Basis | Evidence |
|---|---|---|---|---|---|
| Primary | 54,601 | images | Six CASIA-IrisV4 subsets | official_source_description | hycasia.github.io/dataset |
Counts retain their source-reported units. Additional rows can describe components, paired items, or derivative copies and are not automatically added to the primary quantity.
Notes
The project documentation mirror reports 54,601 images from more than 1,800 genuine and 1,000 virtual subjects, with possible subject overlap across four subsets, and describes the release as public domain. The linked download service may require login.
Access information and download
- CLI
- Python
# Read-only preflight
eyehub download casia_iris_v4 --data-dir ./data --dry-run --json
# Download, only when preflight reports supported behavior
eyehub download casia_iris_v4 --data-dir ./data
from eyedatahub.acquisition import preflight_dataset
from eyedatahub.datasets.registry import REGISTRY
ds = REGISTRY.get_dataset('casia_iris_v4')
print(preflight_dataset(ds, './data')) # no download
Upstream page: hycasia.github.io/dataset
Source-term evidence: hycasia.github.io/dataset
Loader status
This catalog record provides metadata and access instructions, but it does not yet include a standard DatasetSample loader. Inspect the source file structure or contribute a loader before using it in a training pipeline.
Citation
- BibTeX
- Plain text
@misc{casia_iris_v4,
title = { CASIA-IrisV4 Iris Image Database },
note = { Chinese Academy of Sciences Institute of Automation. CASIA Iris Image Database Version 4.0. Dataset documentation },
url = { https://hycasia.github.io/dataset/casia-irisv4/ },
}
Chinese Academy of Sciences Institute of Automation. CASIA Iris Image Database Version 4.0. Dataset documentation.
Source-stated terms
- Raw source string: Public domain; source access terms apply
- Normalized category:
cc0 - Apparent scope:
unknown - Descriptive screening label: Standard label without an explicit NC clause; not a permission finding
⚠️ Source-stated terms, scope, and normalized labels are curation metadata, not legal advice or a permission finding. Review the current official source before transfer or reuse.
Similar resources by shared modality
- nd_iris_0405: ND-IRIS-0405 Iris Image Dataset (64,980 images,
research-only) - ubiris_v2: UBIRIS.v2 Noisy Visible-Wavelength Iris Database (11,102 images,
unknown) - doomgan_ocular_morphs: DOOMGAN Ocular Morph-Attack Dataset (10,000 images,
mit) - mendeley_cust_iris: CUST-Iris (2,880 images,
cc-by) - dryad_sbcc2fr6n: Exploring phenotypic diversity of pigmented traits and iris features in Pakistani population (514 participants,
cc0) - dryad_iris_surface_features: Iris Surface Features Dataset (Not reported,
cc0)