Estimation of surface roughness for turning operations using image texture features

Abstract

Measuring surface roughness is vital to quality control of the machined workpiece. In recent years, vision systems have made image analysis easier and more flexible for measuring surface roughness by using texture features. In this paper, the texture features of the grey-level co-occurrence matrix (GLCM) have been utilized to estimate surface roughness of specimens machined by turning operations. The relationship between GLCM texture features and surface roughness has been investigated to discover which texture features can be used to estimate surface roughness. The correlation coefficient between each texture feature and the arithmetic average height ( Ra) was calculated and discussed. The investigation showed that six texture features are highly correlated with Ra. Therefore, these texture features were used to estimate surface roughness for similar specimens with known values of Ra. The results showed that the maximum percentage of error between the actual Ra and the estimated Ra was about ±7 per cent.