Getting Started

To set up the Generic Platform see the Quick Start User Manual.

To use the generic platform you may find the Generic GUI User Guide to be helpful.

You will also need an iris image dataset, if you don't have one then there are many datasets available via the internet. The image datasets available to researchers that are more commonly used in the literature are as follows.

Chinese Academy of Sciences, Institute of Automation (CASIA)
The Chinese Academy of Sciences’ Institute of Automation (CASIA) datasets are used throughout the world and have been referenced in many publications. There are nine datasets containing 58,241 images for general research purposes. Each image is an 8-bit grey-scale image ranging in size from 320×280 pixels up to 640×480 pixels.
http://biometrics.idealtest.org/

Multimedia University (MMU)
There are two MMU iris datasets; each collected using a different camera. The MMU datasets offer a good selection of ethnicities and image quality, so the algorithm under test is stressed, but, they contain only 1,445 images in total, not many when compared to CASIA’s 58,241.
http://pesona.mmu.edu.my/~ccteo/index.htm

Unconstrained Biometrics: Iris (UBIRIS)
The UBIRIS 1 dataset is similar to the MMU and main CASIA datasets in that it provides consistent close-up images of eyes in two different resolutions, as well as in colour and greyscale. The UBIRIS 2 dataset provides a much wider variety of image qualities and distances than the other iris image datasets. Taken together, these two datasets contain a significant 12,350 images.
http://iris.di.ubi.pt/ubiris1.html
http://iris.di.ubi.pt/ubiris2.html

West Virginia University (WVU)
The West Virginia University iris dataset comprises 865 off-axis iris images, 268 of which were collected with a Sony Cyber Shot DSC F717, while the remaining 597 were collected using a monochrome, black and white camera. There is a slight green hue to the Sony camera images as it was used in infrared mode, but still used all three RGB sensors.
The WVU dataset has quite stringent release pre-requisites and is only available on disc, not via download.
http://www.citer.wvu.edu/biometric_dataset_collections

West Virginia University (WVU) Free
This sub-set of the WVU dataset is provided without restriction by Li alongside his iris recognition code download. It is a very small dataset with only 80 images, but contains images with a greater degree of variation of gaze direction than many others.
http://www.csee.wvu.edu/~xinl/demo/nonideal_iris.html

Indian Institute of Technology (IIT) Delhi
The IIT Delhi iris dataset consists of iris images collected at IIT Delhi. This dataset was acquired using a JIRIS JPC1000 digital CMOS camera, is from 224 users and all the images are in bitmap format. The users were between the ages of 14 and 55 years. The 1120 images are from 176 males and 48 females. All images are at a resolution of 320×240 pixels.
http://www4.comp.polyu.edu.hk/~csajaykr/IITD/Database_Iris.htm

University of Palackého and Olomouc (UPOL)
This dataset contains 384 iris images (3×64 left and 3×64 right). The images are 24-bit, RGB, 576×768 pixels. The irises were scanned using a TOPCON TRC50IA optical device connected to a SONY DXC-950P 3CCD camera. The UPOL dataset is unusual in that a black border surrounds each iris. This can make detection difficult as there is a very sharp boundary outside the actual iris.
http://phoenix.inf.upol.cz/iris/

Iris Challenge Evaluation (ICE) 2005
This dataset contains 3953 greyscale iris images from 132 individuals captured in the near infrared (NIR) by an LG2200 camera. The images are of a single eye, with 1425 images of right-eyes from 124 individuals and 1528 images of left eyes from 120 individuals.
http://iris.nist.gov/ice/