This method  encode the grayscale image by scaling the pixel value into graylevels, then according to the direction of GLCM, the summation of the relation gray levels are calculated.
GLCM also has some well known properties in order to represent GLCM value as features vector.
It returns a measurement of the intensity contrast between a pixel and its neighbour over the whole image.
It returns a measurement of how correlated a pixel is to its neighbour over the whole image
It returns the summation of squared elements in the GLCM.
It returns a value that measures the closeness of the distribution of elements in the GLCM to the GLCM diagonal.
p(i, j) : GLCM value on element (i,j)
N : Number of gray levels used in quantization process
µ : glcm mean
σ2 : The variance of the intensities of all reference pixels in the relationship that contributed to the GLCM
 R. M. Haralick, K. Shanmugam, and I. Dinstein. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6):610–621, Nov 1973. ISSN 0018-9472. doi: 10.1109/TSMC.1973.4309314.
Published at : Updated