Eye Aspect Ratio based Blink Rate detection and its potential use for Parkinsons Disease
Key: GOK+18-1
Author: Augusto Garcia-Agundez, Tobias Ochs, Robert Konrad, Polona Caserman, Stefan Göbel
Date: May 2018
Kind: In proceedings
Book title: IWBBIO 2018 - 6th International Work-Conference on Bioinformatics and Biomedical Engineering
Abstract: Literature shows patients suffering from Idiopathic Parkinsons Disease suffer, among many other symptoms, a reduced blinking rate. We believe this symptom could be easily detected by measuring the blink rate in the background while they use their computer. Objective. The goal of this contribution is to design an algorithm for video-based Blink Detection. Methods. An algorithm based on the eye aspect ratio method, OpenCV and a simple threshold system was developed. Results. Our algorithm was evaluated with n=10 healthy users, as well as previously available databases, and an average precision/recall of 82%/75% was achieved. Conclusion. Background blink rate estimation using an integrated web camera is accurate and feasible in real time by using the EAR method, and may be implemented into PD management procedures.

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.