Visual Inspection of Machined Parts

The problem of automating industrial inspection tasks is an interesting and challenging one. Since modern design techniques produce geometric models of the parts being designed, it is natural to extend these models to the task of inspecting the parts that are manufactured. Although many special purpose inspection systems have been developed, general purpose systems utilizing CAD models of the parts are still in the research stage. While it is easy to define ad hoc algorithms for inspection, it is much more difficult to justify the algorithms with solid theory. In this paper we describe a CAD-model-based machine vision system for dimensional inspection of machined parts, with emphasis on the theory behind the system. The original contributions of our work are: 1) the use of precise definitions of geometric tolerances suitable for use in image processing, 2) the development of measurement algorithms corresponding directly to these definitions, 3) the derivation of the uncertainties in the measurement tasks, and 4) the use of this uncertainty information in the decision-making process. Our experimental results have verified the uncertainty derivations statistically, proved that the error probabilities obtained by propagating uncertainties are lower than those obtainable without uncertainty propagation, and demonstrated that the inspection system responds in a predictable manner when applied to deformed objects.