Skin detection using HSV & YCbCr color space (Python, OpenCV)
The above entire procedure is applied to each and every pixel of the image.
The RGB image value is converted to HSV as well as YCbCr value, the HSV and YCbCr value of each pixel is compared to the standard values of a skin pixel and the decision is made whether the pixel is a skin pixel or not depending on whether the values lie in a range of predefined threshold values for each parameter.
The ranges for a skin pixel used in this algorithm are as follows:
0<=H<=17 and 15<=S<=170 and 0<=V<=255
and
0<=Y<=255 and 135<=Cr<=180 and 85<=Cb<=135
Please cite this method as follow :
Djamila Dahmani, Mehdi Cheref, Slimane Larabi, Zero-sum game theory model for segmenting skin regions, Image and Vision Computing, Volume 99, 2020, 103925,ISSN 0262-8856, https://doi.org/10.1016/j.imavis.2020.103925.
URL : http://sun.aei.polsl.pl/~mkawulok/gestures/
URL : http://www.sel.eesc.usp.br/sfa/
In the following images you will see the skin detection results of each color space threshold, and the result of their association
In the following images you will see the skin detection results of this methode using images from two databases SFA and HGR
