A surface roughness measurement technique, based on an area measurement method using a computer vision system, was investigated for applicability to in-process inspection of surface quality during a machining process. The vision system uses a monochrome CCD camera to provide a gray-scale image based on the pattern of light scattered from an area of the machined piece. This gray-scale image is sent to image manipulation software for analysis. For this investigation, an optical camera was used to photograph four aluminum samples with different roughnesses, and the resulting photographs were scanned into a computer using an 8-bit flat-bed scanner to produce the digital image used by the image manipulation software. Three parameters were derived from the images based on their gray-scale histograms, and these parameters were plotted against the corresponding average roughness (Ra) values determined using a stylus instrument. The resulting correlation curves were inspected to determine which optical parameter was most suitable for use in the system, based on relative accuracy and sensitivity of the parameters to changes in Ra.