Enhanced skin colour classifiers using pixel-based and region-based modelling techniques

Abstract

Skin colour detection is frequently been used for searching people, face detection, pornographic filtering and hand tracking. Skin colour detection is a process to determine whether a desired pixel or a group of pixels belongs to skin or non-skin. The presence of skin or non-skin in digital image can be determined by manipulating pixels' colour and/or pixels' texture. For still image, skin colour detection is a task where an image is produced as input to the process and its output is a set of positions of skin pixels or non-skin pixels. The process of skin detection involves classification technique, which is carried out at an individual pixel or a group of pixels. Thus, skin classification technique can be categorised into two categories; pixel-based and region-based classification techniques.