SURFACE TEXTURE MEASUREMENT BY COMPUTER VISION

A fully automated, non-contacting, full field method is presented to measure the surface roughness parameters using a computer vision system and image processing techniques. The texture features, namely, coarseness, contrast and roughness are extracted from digitized images of standard surface roughness comparator plates and correlated with the arithmetic average roughness (Ra) of the surface. The vision, system offers a fast and accurate method for the on-line automated surface roughness inspection of machined components