Vision-based 3D head pose tracking using fuzzy classifier-based face segmentation and silhouette volume intersection

This electronic document is a “live” template and already defines the components of your paper [title, text, heads, etc.] in its style sheet. **CRITICAL: Do Not Use Symbols, Special Characters, or Math in Paper Title or Abstract. This paper proposes a three-dimensional (3D) head pose tracking method using fuzzy classifier-based face segmentation and silhouette volume intersection techniques. The fuzzy classifier consists of clustering-based antecedent parameter learning and linear support vector machine-based consequent parameter learning. A stereo webcam is used to capture two images at the same time. The fuzzy classifier is applied to segment two-dimensional (2D) human face skin pixels in the Cb and Cr color space and in each of the two captured images. Based on the 2D segmented regions, the silhouette volume intersection method is used to find the regions of the face in 3D space. The average 3D coordinate of the face region is computed and is used to estimate the orientation of the face in real-time. This paper sets up a real-time 3D virtual head pose following system to verify the effectiveness of the proposed approach.