Gi4E Database

Introduction

We have created a public database of images for iris center and eye corner detection. The database consists of a set of 1339 images acquired with a standard webcam, corresponding to 103 different subjects and 13 images each. Every set of 13 images consists of 12 images in which the user gazes at different points in the screen and another image in which the user’s eyes are closed.

The images are provided in png format (lossless). They have a resolution of 800×600 pixels. Images are associated to a ground-truth text file. It contains manually annotated 2D iris and corner points (in pixels). For more information about the database, please refer to the paper.

Sample images taken from the database:

For more detailed information about the database, please refer to:
Arantxa Villanueva, Victoria Ponz, Laura Sesma‐Sanchez, Mikel Ariz, Sonia Porta, and Rafael Cabeza, “Hybrid method based on topography for robust detection of iris center and eye corners”, ACM Transactions on Multimedia Computing, Communications and Applications (TOMCCAP). 9, 4 (2013).

 

Download the database

The database is publicly available after registering. You can download it here

 

Submit your results

We invite other researchers to run their iris center algorithms with this database. If you are interested in sharing your results with other researchers, please submit your estimation here. After submitting your estimation, your results will appear in the leaderboard. If you are satisfied with the results, you can submit the information about your algorithm and research.

 

References

This database is publicly available for research purposes. If you use it, please cite this paper:

[1] Arantxa Villanueva, Victoria Ponz, Laura Sesma‐Sanchez, Mikel Ariz, Sonia Porta, and Rafael Cabeza, “Hybrid method based on topography for robust detection of iris center and eye corners”, ACM Transactions on Multimedia Computing, Communications and Applications (TOMCCAP). 9, 4 (2013).