Machine Learning-Based Facial Beauty Prediction and Analysis of Frontal Facial Images Using Facial Landmarks and Traditional Image Descriptors

Table 3

Statistical descriptors for GLCM.

Statistic	Description	Justification	Formula
Contrast	This measure returns the intensity contrast between a pixel and its neighbor over the image.	This feature can help in measuring the number of local variations in the image.
Homogeneity	This measure measures the similarity between the diagonal elements of the GLCM and the distribution of elements in the GLCM	This measure helps in finding out the degree to which each pixel differs from the other.
Correlation	This measure returns the correlation between a pixel and its neighbor over the whole image.	This feature can help in measuring how much a pixel relates to the whole image.
Energy	This measure measures the sum of squared elements in GLCM. It is also known as uniformity.	This measure helps in finding out the disorders in the texture of an image.