Exploiting Fuzzy Approximator for Head Pose Estimation
Head pose estimation is an important problem in computer vision and also a key task for visual surveillance, human computer interaction and face recognition applications. Most of the works in this field suffer from lack of continuous estimating of the head pose. Fuzzy systems are known as universal approximator capable of approximating an unknown function by having just few limited information. In this paper, a new approach is proposed for estimating the rotation angle of the head along horizontal axis based on a fuzzy approximator which is able to provide a continuous estimate of the head along horizontal axis with high acceptable accuracy, low computational cost while avoiding from getting involved into complex mathematical equations. Experiments on more than 200 images showed less than 9° of mean absolute error in estimation which is a high desirable accuracy.
component Head pose estimation Fuzzy approximator
Maryam Baradaran-K Saeed Toosizadeh Mohammad-R.Akbarzadeh-T S.Kazem Shekofteh
Department of Computer Engineering, Islamic Azad University, Mashhad Branch,Mashhad, Iran Department of Computer Engineering, Islamic Azad University,Mashhad Branch, Mashhad, Iran Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran
国际会议
北京
英文
323-326
2010-09-18（万方平台首次上网日期，不代表论文的发表时间）