Table 4.

List of GLCM features and their associated equations.

Features	Equations
Autocorrelation	${\displaystyle \sum }_i{\displaystyle \sum }_j\left(i\bullet j\right)p(i,j)$
Contrast	${\displaystyle \sum }_i{\displaystyle \sum }_j|i-j{|}^{2}p(i,j)$
Correlation I	${\displaystyle \sum }_i{\displaystyle \sum }_j\frac{(i-{\mu }_x)(j-{\mu }_y)p(i,j)}{{\sigma }_x{\sigma }_y}$
Correlation II	${\displaystyle \sum }_i{\displaystyle \sum }_j\frac{\left(i\bullet j\right)p\left(i,j\right)-{\mu }_x{\mu }_y}{{\sigma }_x{\sigma }_y}$
Cluster Prominence	${\displaystyle \sum }_i{\displaystyle \sum }_j{\left(i+j-{\mu }_x-{\mu }_y\right)}^{4}p(i,j)$
Cluster Shade	${\displaystyle \sum }_i{\displaystyle \sum }_j{\left(i+j-{\mu }_x-{\mu }_y\right)}^{3}p(i,j)$
Dissimilarity	${\displaystyle \sum }_i{\displaystyle \sum }_j\left|i-j\right|\bullet p(i,j)$
Energy	${\displaystyle \sum }_i{\displaystyle \sum }_{j}p(i,j{)}^2$
Entropy	$-{\displaystyle \sum }_i{\displaystyle \sum }_{j}p(i,j)\bullet \log \left(p\left(i,j\right)\right)$
Homogeneity I	${\displaystyle \sum }_i{\displaystyle \sum }_j\frac{p(i,j)}{1+|i-j|}$
Homogeneity II	${\displaystyle \sum }_i{\displaystyle \sum }_j\frac{p(i,j)}{1+|i-j{|}^2}$
Maximum Probability	max i,j p(i, j)
Sum of square	${\displaystyle \sum }_i{\displaystyle \sum }_j(i-v{)}^{2}p(i,j)$
Sum average	${\displaystyle \sum }_{i=2}^{2L}i\bullet p_{x+y}(i)$
Sum energy	$-{\displaystyle \sum }_{}^{2L}{p}_{x+y}(i)\bullet \log \left(p_{x+y}\left(i\right)\right)$
Sum variance	${\displaystyle \sum }_{i=2}^{2L}(i-Sum\hspace{0.17em}\hspace{0.17em}engery{)}^2\bullet p_{x+y}(i)$
Difference variance	${\displaystyle \sum }_{i=0}^{L-1}{i}^2\bullet p_{x-y}(i)$
Difference entropy	$-{\displaystyle \sum }_{i=0}^{L-1}{p}_{x-y}(i)\bullet \mathrm{l}\mathrm{o}\mathrm{g}(p_{x-y}\left(i\right))$
Information measure of correlation I	$\frac{\left(-{\sum }_i^{}{\sum }_j^{}p\left(i,j\right)·\log \left(p\left(i,j\right)\right)\right)-\left(-{\sum }_i^{}{\sum }_j^{}p\left(i,j\right)·\log \left(p_x\left(i\right)p_y\left(j\right)\right)\right)}{\max \left(-{\sum }_i^{}{p}_x\left(i\right)·\log \left(p_x\left(i\right)\right),-{\sum }_i^{}{p}_y\left(i\right)·\log \left(p_y\left(i\right)\right)\right)}$
Information measure of correlation II	${\left(1-\exp \left[-2\left(\left(-\sum _i\sum _j{p}_x\left(i\right)p_y\left(j\right)·\log (p_x\left(i\right)p_y\left(j\right)))-\left(-\sum _i\sum _{j}p\left(i,j\right)·\log (p\left(i,j\right)\right)\right)\right)\right]\right)}^{1/2}$
Inverse Difference Normalized	${\displaystyle \sum }_i{\displaystyle \sum }_j\frac{p(i,j)}{1+|i-j{|}^2/L}$
Inverse difference moment normalized	${\displaystyle \sum }_i{\displaystyle \sum }_i\frac{p(i,j)}{1+(i-j{)}^2/L}$

p(i, j) is the (i, j)^th entry of the cooccurrence probability matrix, and L represents the number of gray levels used, while μ_x, μ_y and σ_x, σ_y are the mean and standard deviation of the p.