Table 1.

Shape, texture and color features of milled rice samples obtained from image analysis

	Shape and size features
Feature	Major axis length		Minor axis length		Equivalent diameter	Perimeter		Solidity
Feature no.	F1		F2		F3	F4		F5
	Texture features
Feature	Contrast		Energy		Correlation	Homogeneity
Formula	${\displaystyle \sum _{i=1}^k}{\displaystyle \sum _{j=1}^k{\left(i-j\right)}^2}{p}_{\mathit{ij}}$		${\displaystyle \sum _{i=1}^k}{\displaystyle \sum _{j=1}^k{p_{\mathit{ij}}}^2}$		${\displaystyle \sum _{i=1}^k}{\displaystyle \sum _{j=1}^k{\left(i-j\right)}^2}{p}_{\mathit{ij}}$	${\displaystyle \sum _{i=1}^k}{\displaystyle \sum _{j=1}^k\frac{p_{\mathit{ij}}}{1+\left|i-j\right|}}$
Feature no.	F6		F7		F8	F9
	Color features in RGB Space*
Feature	Mean [μ=$\frac{{\sum }_{x=0}^{z-1}h\left(x\right)}{Z}$] for:
	R	G		B	$\frac{R}{R+G+B}$	$\frac{G}{R+G+B}$	$\frac{B}{R+G+B}$
Feature no.	F10	F11		F12	F13	F14	F15
Feature	Mean [μ=$\frac{{\sum }_{x=0}^{z-1}h\left(x\right)}{Z}$] for:
	R-G			G-B		R-B
Feature no.	F16			F17		F18
Feature	Variance [σ=$\frac{{\sum }_{x=0}^{z-1}{\left(h\left(x\right)-\mu \right)}^2}{Z}$] for:
	R	G		B	$\frac{R}{R+G+B}$	$\frac{G}{R+G+B}$	$\frac{B}{R+G+B}$
Feature no.	F19	F20		F21	F22	F23	F24
Feature	Variance [σ=$\frac{{\sum }_{x=0}^{z-1}{\left(h\left(x\right)-\mu \right)}^2}{Z}$] for:
	R-G			G-B		R-B
Feature no.	F25			F26		F27
Feature	Skewness [s=$\frac{{\sum }_{x=0}^{z-1}{\left(h\left(x\right)-\mu \right)}^3}{{\mathit{Z\sigma }}^3}$] for:
	R	G		B	$\frac{R}{R+G+B}$	$\frac{G}{R+G+B}$	$\frac{B}{R+G+B}$
Feature no.	F28	F29		F30	F31	F32	F33
Feature	Skewness [s=$\frac{{\sum }_{x=0}^{z-1}{\left(h\left(x\right)-\mu \right)}^3}{{\mathit{Z\sigma }}^3}$] for:
	R-G			G-B		R-B
Feature no.	F34			F35		F36
Feature	Kurtosis [k= $\frac{{\sum }_{x=0}^{z-1}{\left(h\left(x\right)-\mu \right)}^4}{{\mathit{Z\sigma }}^4}-3$] for:
	R	G		B	$\frac{R}{R+G+B}$	$\frac{G}{R+G+B}$	$\frac{B}{R+G+B}$
Feature no.	F37	F38		F39	F40	F41	F42
Feature	Kurtosis [k= $\frac{{\sum }_{x=0}^{z-1}{\left(h\left(x\right)-\mu \right)}^4}{{\mathit{Z\sigma }}^4}-3$] for:
	R-G			G-B		R-B
Feature no.	F43			F44		F45
	Color features in HSV space
Feature	Mean [μ=$\frac{{\sum }_{x=0}^{z-1}h\left(x\right)}{Z}$] for:
	H			S		V
Feature no.	F46			F47		F48
	Color features in L*a*b* space
Feature	Mean [μ=$\frac{{\sum }_{x=0}^{z-1}h\left(x\right)}{Z}$] for:
	L			a*		b*
Feature no.	F49			F50		F51
	Color features in YCbCr color map
Feature	Mean [μ=$\frac{{\sum }_{x=0}^{z-1}h\left(x\right)}{Z}$] for:
	Y			Cb		Cr
Feature no.	F52			F53		F54
	Color features in NTSC system
Feature	Mean [μ=$\frac{{\sum }_{x=0}^{z-1}h\left(x\right)}{Z}$] for:
	Yi			I		Q
Feature no.	F55			F56		F57

*h(x) is the grey level of pixels in the image with a pixel position of x, x can take any value between 1 and z = m $\times$ n, where m and n are row and column numbers in the image matrix, respectively

*μ, σ, S, and K are the Mean, Variance, Skewness, and Kurtosis of image pixels, respectively