Open Access Research Article

Automatic Eye Winks Interpretation System for Human-Machine Interface

Che Wei-Gang1*, Chung-Lin Huang12 and Wen-Liang Hwang3

Author Affiliations

1 Department of Electrical Engineering, National Tsing-Hua University, Hsin-Chu, Taiwan

2 Department of Informatics, Fo-Guang University, I-Lan, Taiwan

3 Institute of Information Science, Academic Sinica, Taipei, Taiwan

For all author emails, please log on.

EURASIP Journal on Image and Video Processing 2007, 2007:065184  doi:10.1155/2007/65184

Published: 8 October 2007

Abstract

This paper proposes an automatic eye-wink interpretation system for human-machine interface to benefit the severely handicapped people. Our system consists of (1) applying the support vector machine (SVM) to detect the eyes, (2) using the template matching algorithm to track the eyes, (3) using SVM classifier to verify the open or closed eyes and convert the eye winks into a sequence of codes (0 or 1), and (4) applying the dynamic programming to translate the code sequence to a certain valid command. Different from the previous eye-gaze tracking methods, our system identifies the open or closed eye, and then interprets the eye winking as certain commands for human-machine interface. In the experiments, our system demonstrates better performance as well as higher accuracy.