Tuyển tập báo cáo các nghiên cứu khoa học quốc tế ngành hóa học dành cho các bạn yêu hóa học tham khảo đề tài: Research Article Automatic Eye Winks Interpretation System for Human-Machine Interface | Hindawi Publishing Corporation EURASIP Journal on Image and Video Processing Volume 2007 Article ID 65184 9 pages doi 2007 65184 Research Article Automatic Eye Winks Interpretation System for Human-Machine Interface Che Wei-Gang 1 Chung-Lin Huang 1 2 and Wen-Liang Hwang3 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 Received 2 January 2007 Revised 30 April 2007 Accepted 21 August 2007 Recommended by Alice Caplier 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. Copyright 2007 Che Wei-Gang et al. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use distribution and reproduction in any medium provided the original work is properly cited. 1. INTRODUCTION Recently there has been an emerging community of machine perception scientists focusing on automatic eye detection and tracking research. It can be applied for vision-based human-machine interface HMI applications such as monitoring human vigilance 1-6 and assisting the disable 7 8 . The eye detection and tracking approaches can be classified into two categories CCD camera-based
