Evaluation of surface roughness using machine vision

In this work, a machine vision system has been utilized to determine the surface roughness of the milled surfaces. For checking the effectiveness of the machine vision based results, a wide range of surface roughness were generated on CNC milling centre using Design of Experiments (DoE) technique. Stylus-based parameters Ra and Rsm were acquired and compared with vision-based parameters (Ga, R1, R2, CV, contrast etc). Model equations have been developed, in terms of the machining parameters, image parameters and machining and image parameters using response surface methodology on the basis of experimental results. The experimental result indicates that the surface roughness could be estimated/predicted with a reasonable accuracy using machine vision.