Automatic Characterization of the Visual Appearance of Industrial Materials through Colour and Texture Analysis: An Overview of Methods and Applications

Table 1

Method and related parameters.

Class	Method	Parameters
Spectral	R, G, B, means	None
	Colour histogram	Number of quantization levels
	Chromaticity moments	Number of quantization levels.
	Colour centiles	Number of percentiles
Spatial	GLCM	Distance, co-occurrence directions
	LBP^ri	Radius, number of pixels
	CCR^ri	Radius, number of pixels, and thresholding method
	Gabor filters	Number of frequencies, number of orientations, maximum frequency, width and length of the Gaussian envelope, and frequency ratio
Hybrid	OCLBP^ri	Radius, number of pixels
	Integrative CM	Distance, co-occurrence directions
	Ranklets	Radius, number of pixels
	LBP^ri + colour centiles	Radius, number of pixels, and number of percentiles