Comparative Study of Statistical Skin Detection Algorithms for Sub-Continental Human Images

摘要

Object detection has been a focus of research in human-computer interaction.Skin area detection has been a key to different recognitions like facerecognition, human motion detection, pornographic and nude image prediction,etc. Most of the research done in the fields of skin detection has been trainedand tested on human images of African, Mongolian and Anglo-Saxon ethnicorigins. Although there are several intensity invariant approaches to skindetection, the skin color of Indian sub-continentals have not been focusedseparately. The approach of this research is to make a comparative studybetween three image segmentation approaches using Indian sub-continental humanimages, to optimize the detection criteria, and to find some efficientparameters to detect the skin area from these images. The experiments observedthat HSV color model based approach to Indian sub-continental skin detection ismore suitable with considerable success rate of 91.1% true positives and 88.1%true negatives.