Idea wins two prestigious awards from IEEE and EESTEC
Evangelos Skodras, a PhD student at the University of Patras, has recently won two prestigious awards for an idea developed under guidance and a little coding help from myself.
The prototype developed makes use of Evangelos' innovative algorithm for eye tracking in low-resolution images, uses color information to derive a novel eye map that emphasizes the iris area and a radial symmetry transform which operates both on the original eye images and the eye map. His algorithm was implemented in Android, using the OpenCV library. To find a practical application for his algorithm, I suggested that we work on a system that allows users to enter text using a tablet computer, using their gaze only. The system works by assigning letters to four buttons on the corners of the screen. The user fixes their gaze for a few milliseconds on each of the buttons to select it and to ambiguously input letters belonging to the letter group. The OpenAdapTXT disambiguation engine then undertakes the task of "guessing" which word the user tried to input. Alternatives are presented to the user at the centre of the screen, and the user can scroll through each alternative, again simply by gazing.
Our idea won the 2015 awards in the following categories:
- Most innovative app, Electical Engineering Students European Association (EESTEC), 2015 International Android Competition;
- Computer Society Award, IEEE Mobile Application Development Contest 2015
A video of the application and how it works can be found on YouTube (Video 1 - demo) and (Video 2 - how it works).