DeepVOG

DeepVOG is a framework for pupil segmentation and gaze estimation based on a fully convolutional neural network.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

Prerequisites

To run DeepVOG, you need to have a Python distribution (we recommend Anaconda) and the following Python packages:

scikit-image
Tensorflow
etc.

Installing

A step by step series of examples that tell you how to get DeepVOG running.

Publication and Citation

If you plan to use this work in your research or product, please cite this repository and our publication pre-print on arXiv.

Authors

• Yiu Yuk Hoi - Implementation and validation
• Seyed-Ahmad Ahmadi - Research study concept
• Moustafa Aboulatta - Initial work

License

This project is licensed under the GNU General Public License v3.0 (GNU GPLv3) License - see the LICENSE file for details

Acknowledgments

We thank our fellow researchers at the German Center for Vertigo and Balance Disorders for help in acquiring data for training and validation of pupil segmentation and gaze estimation. In particular, we would like to thank Theresa Raiser, Dr. Virginia Flanagin and Prof. Dr. Peter zu Eulenburg.