Human Skin Detection in Color Images Using Deep Learning

Top

2. Methods For Skin Color Detection

Different methods have been used for detecting human skin in images. Among them Gaussian, rule-based, and neural networks are some of the more popular approaches.

The Gaussian model (Wu et al., 2008) uses the YCbCr color space. The density function for Gaussian variable is used to make a decision of whether or not a pixel belongs to human skin. The parameters of the density function are calculated using training images. If the probability is more than a given threshold then that pixel is considered as human skin. The density function for Gaussian variable is:

Where, , , and the parameters are:

,

Chen et al. (2008) used conditional probability density function and Bayesian classification in order to define some rules for detecting human skin. RGB was used as color space. The rules are:

With

Kovac et al. (2003) introduced two sets of rules one for indoor images and one for images taken in daylight illumination. Kovac also used RGB as color space. The rules are:For indoor images:

For images taken in daylight illumination: