A Knowledge-based System For Hair Region Segmentation
Zhi-Qiang Liu, Jingwei Guo, Len T. Bruton · Information Sciences, Signal Processing and their Applications · 1996
The ease with which humans recognize the hair often leads to the incorrect assumption that this capability is easy to automate. Currently, the task of locating the hair region in a facial image requires manual process. In this paper we ezamine diflerent aspects of this hair region segmentation problem and develop an automatic system for such a problem. The system incorporates the human knowledge about where the hair ie usually located in a facial image. Segmentation is perfbnned via classification of image pixels and is based on both textural and geometrical features. Experiments have shown that the segmentation results are generally >;atisfactory and are at least comparable to the perfomlance of manual extraction.