A Method for Measurement of Workpiece form Deviations Based on Machine Vision

Machine vision has been studied for measurements of workpiece form deviations due to its ease of automation. However, the measurement accuracy limits its wide implementation in industrial applications. In this study, a method based on machine vision for measurement of straightness, roundness, and cylindricity of a workpiece is presented. A subsumed line search algorithm and an improved particle swarm optimization algorithm are proposed to evaluate the straightness and roundness deviations of the workpiece. Moreover, an image evaluation method of cylindricity deviation by the least-square fitting of the circle’s center coordinates is investigated. An image acquisition system incorporating image correction and sub-pixel edge positioning technology is developed. The performance of the developed system is evaluated against the measurement results of the standard cylindricity measuring instrument. The differences in the measurement of straightness, roundness, and cylindricity are −4.69 μm, 3.87 μm, and 8.51 μm, respectively. The proposed method would provide a viable industrial solution for the measurement of workpiece form deviations.