Table A1.

Formulae to calculate first order features from the gray-scale image.

Feature Name	Formulae
Mean	$\mu =\frac{1}{W·H}{\sum }_{x=0}^{W-1}{\sum }_{y=0}^{H-1}I\left(x,y\right)={\sum }_{i=0}^{G-1}i·h\left(i\right)$	(A1)
Variance	${\sigma }^2=\frac{1}{W·H}{\sum }_{x=0}^{W-1}{\sum }_{y=0}^{H-1}{(I\left(x,y\right)-\mu )}^2={\sum }_{i=0}^{G-1}{(i-\mu )}^2·h\left(i\right)$	(A2)
Skewness	${\sigma }^{-3}{\sum }_{i=0}^{G-1}{(i-\mu )}^3·h\left(i\right)$	(A3)
Kurtosis	${\sigma }^{-4}{\sum }_{i=0}^{G-1}{(i-\mu )}^4·h\left(i\right)-3$	(A4)
Percentile	${\sum }_{i=0}^{G-1}h\left(i\right)\ge percentile$	(A5)