A mathematical model for reducing the likely spectrum of human skin tones in the RGB color space

Skin detection techniques are widely applied to locate and track the human body for the purpose of further recognition. Some advantages of face detection based on skin color in relation to other techniques are faster processing and invariance. In this work there are presented experiments and a model that improves precision and processing time for human skin detection. The model found a more likely and reduced amplitude of spectrum of colors in the RGB system for detecting skin. Applied to 16,777,216 possible combinations of colors in the RGB system the 6 rules considered relevant by the proposed mathematical model allowed a 98.3657% reduction of the spectrum. Experimental results show the accuracy of the method for detecting human skin tones.