A Survey on Skin Segmentation Techniques in Multimedia

The segmentation of skin regions is a pre requisite step in many computer vision applications dealing with the detection and recognition of humans and their activities. Such systems can be found in the fields of surveillance, human computer interaction and face recognition. In a general situation, skin detectors like Gaussian mixture models or skin probability maps achieve acceptable skin segmentation results. Although, color cues have the advantage to be relatively invariant regarding scale and orientation, the utilization color information is often a challenging task, as in images, the appearance of the skin color is dependent on different factors, like illumination condition, ethnicity, camera characteristics etc. However, the false positive rate increases considerably when the skin tones are in shadow or when skin-like background objects are under similar illumination. This paper presents a survey on various skin segmentation techniques to provide an accurate and better segmentation result.