I am still new to image processing and machine intelligence. I wanted to make a Python program that can isolate an image of a hand from the background to detect a specific hand gesture, so I came to this paper (Hand Gesture Based Recognition And Voice Conversion System For Physically Disabled People), and the writer states in this paper that:
Pixels of skin color in YCbCr color space satisfies Gaussian distribution. Experiments show that using the single Gaussian model (SGM) to segment the gesture image is effective and its computational complexity is small
I don't understand how the skin color follows the Gaussian distribution in YCbCr colour space. If so, what's the variance and mean of skin color in that space?