作者: G. Gomez , M. Sanchez , L. Enrique Sucar
关键词:
摘要: We present a comprehensive and systematic approach for skin detection. have evaluated each component of several colour models, then we selected suitable model Such is well-known in the machine learning community as attribute selection. After listing top components, exemplify that mixure components can discriminate very well both indoor outdoor scenes. The spawning space created by such componens nearly convex, therefore it allow us to use even simple rules non-skin points. These recognise 96% points with just 11% false positives. This data analysis will help many detection systems.