Real Time Eye Tracking in Unconstrained Environments
In this paper, an effective method for human eye tracking and also decreasing the current challenges and problems in its algorithms, possibly as real time and for unconstrained environments has been proposed. In this method, firstly face has been detected and segmented from the remaining parts to make the searching area in tracking stage, narrower and processing speed higher. Then eye area is determined and eye pupils are detected in the specified area. In the proposed method, to support tracking in eye occlusion state, corner detection has been additionally used. Experimental results show the potential of this method for real time eye tracking in unconstrained environments with existence of complex background, head and face rotation, beard, makeup, eye glasses and veil, even while the eyes are closed. The correct recognition rate of the proposed method is about 91.9%.
Keywords: Eye Detection, Face Detection, Eye Tracking, Kalman Filter, Corner Detection, Harris Algorithm.
Download Full-Text
ABOUT THE AUTHORS
Majid Tajeri
Majid Tajeri received the B.S. degree in computer engineering from Kashan Branch, Islamic Azad University, Kashan, Iran, in 2009. He is currently a graduate student in the Department of Computer Engineering at Arak Branch, Islamic Azad University, Arak, Iran. His research interests include image processing and pattern recognition.
Mahmoud Mahlouji
Mahmoud Mahlouji received the B.S. degree in telecommunications engineering from Sharif University of Technology, Tehran, Iran, in 1990, the M.Sc. degree in electronics engineering from Sharif University of Technology, Tehran, Iran, in 1993, and the Ph.D. degree in telecommunications engineering from Science and Research Branch, Islamic Azad University, Tehran, Iran, in 2008. At present he is an assistant professor of the Electrical and Computer Engineering Department, Kashan Branch, Islamic Azad University, Kashan, Iran. His current interests are in image processing, pattern recognition, neural networks, computer vision, and iris recognition.
Hossein Ebrahimpour-Komleh
Hossein Ebrahimpour-Komleh is currently an assistant professor at the Department of Electrical and Computer Engineering at the University of Kashan, Kashan, Iran. His main area of research includes Computer Vision, Image Processing, Pattern Recognition, Biometrics, Robotics, Fractals, chaos theory and applications of Artificial Intelligence in Engineering. He received his Ph.D. degree in Computer engineering from Queensland University of technology, Brisbane, Australia in 2006. His Ph.D. research work is on the Fractal Techniques for face recognition. From 2005 to 2007 and prior to joining the University of Kashan, he was working as a Post-doc researcher in the University of Newcastle, NSW, Australia and as a visiting scientist in CSRIO Sydney. Hossein Ebrahimpour-Komleh has B.Sc. and M.Sc. degrees both in computer engineering from Isfahan University of Technology (Isfahan, Iran) and Amirkabir University of Technology (Tehran, Iran,) respectively. He has served as the editorial board member and reviewer of several journals and international and national conferences.
Majid Tajeri
Majid Tajeri received the B.S. degree in computer engineering from Kashan Branch, Islamic Azad University, Kashan, Iran, in 2009. He is currently a graduate student in the Department of Computer Engineering at Arak Branch, Islamic Azad University, Arak, Iran. His research interests include image processing and pattern recognition.
Mahmoud Mahlouji
Mahmoud Mahlouji received the B.S. degree in telecommunications engineering from Sharif University of Technology, Tehran, Iran, in 1990, the M.Sc. degree in electronics engineering from Sharif University of Technology, Tehran, Iran, in 1993, and the Ph.D. degree in telecommunications engineering from Science and Research Branch, Islamic Azad University, Tehran, Iran, in 2008. At present he is an assistant professor of the Electrical and Computer Engineering Department, Kashan Branch, Islamic Azad University, Kashan, Iran. His current interests are in image processing, pattern recognition, neural networks, computer vision, and iris recognition.
Hossein Ebrahimpour-Komleh
Hossein Ebrahimpour-Komleh is currently an assistant professor at the Department of Electrical and Computer Engineering at the University of Kashan, Kashan, Iran. His main area of research includes Computer Vision, Image Processing, Pattern Recognition, Biometrics, Robotics, Fractals, chaos theory and applications of Artificial Intelligence in Engineering. He received his Ph.D. degree in Computer engineering from Queensland University of technology, Brisbane, Australia in 2006. His Ph.D. research work is on the Fractal Techniques for face recognition. From 2005 to 2007 and prior to joining the University of Kashan, he was working as a Post-doc researcher in the University of Newcastle, NSW, Australia and as a visiting scientist in CSRIO Sydney. Hossein Ebrahimpour-Komleh has B.Sc. and M.Sc. degrees both in computer engineering from Isfahan University of Technology (Isfahan, Iran) and Amirkabir University of Technology (Tehran, Iran,) respectively. He has served as the editorial board member and reviewer of several journals and international and national conferences.