LAVI Iris Database - DB2

1. Data set information:

The LAVI Iris Database DB2 contains 157.842 iris images of 53 eyes from 53 volunteers. The iris images were captured using JAI AD-080GE camera in diferents sessions.
In each session, it was acquired one video (.avi) of the right eye from each volunteer. Some volunteers contributed with two to four video samples.
All iris images are 8 bit gray-level TIFF files and the image resolution is 1024x768 pixels.
The file name of each image in the LAVI-Iris-Database-DB2 is unique to each other and denotes some useful properties associated with the image.
The file images of LAVI-Iris-Database-DB2 are stored as:

XXX (folder)

XXX: the unique identifier of the subject in the subset (class)

Each folder contains two file types:

XXX_Sy.avi : The complete video acquired by our system as described in the following publication:

DE SOUZA, J. M.; GONZAGA, A.; Human iris feature extraction under pupil size variation using local texture descriptors, Multimedia Tools and Applications, Springer, March 2019, 30 p.
https://doi.org/10.1007/s11042-019-7371-4

XXX_Sy_000_999.zip : All the 1000 individual frames of the class XXX, captured by the sample Sy

2. File information:
Each file in each zipped file has the following name:

XXX_Sy_zzz.tiff (one video frame or one class element)

XXX: the unique identifier of the subject (class)
y: the index of sample in the class
zzz: the index of the frame in the sample


Citation Policy:

If you publish material based on databases obtained from this repository, then, in your acknowledgements, please note the assistance you received by using this repository. This will help others to obtain the same data sets and replicate your experiments.
We suggest the following reference format for referring to this database:

DE SOUZA, J. M.; GONZAGA, A.; Human iris feature extraction under pupil size variation using local texture descriptors, Multimedia Tools and Applications, Springer, March 2019, 30 p.
https://doi.org/10.1007/s11042-019-7371-4

Copyright Note and Contacts:

The database is released for research and educational purposes. We hold no liability for any undesirable consequences of using the database. All rights of the LAVI database are reserved. Any person or organization is not permitted to distribute, publish, copy, or disseminate this database. In all documents and papers that report experimental results based on this database,  a reference to “LAVI Iris Database DB2, http://http://imagem.sel.eesc.usp.br/base/iris/index.html” should be included. 

Professor Adilson Gonzaga
Department of Electrical Engineering - EESC/USP,
Av. Trabalhador São Carlense, 400 São Carlos, SP, Brazil
CEP 13566-590
agonzaga@sc.usp.br