Head Pose Estimation Using Fuzzy Approximator Augmented by Redundant Membership Functions

Estimating the head pose of a human is a key task for human computer interaction, visual surveillance and face recognition applications hence an important problem in computer vision. 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 while gaining high accuracy. In this paper, a new approach is proposed for estimating the rotation angle of the head along horizontal axis based on a fuzzy approximator in which the membership functions are constructed in a way that there is no manual tuning needed since for each range in the input variable which is not covered completely, a new membership function is introduced. The proposed method is able to provide a continuous estimate of the head along horizontal axis with high accuracy, low computational cost while avoiding from getting involved into complex mathematical equations. Experiments on images from two standard well-known databases showed less than 7° of average absolute error in estimation which is a significant improvement over the method based on the simple membership functions.