Intrinsic characteristics as the interface between CAD and machine vision systems

Computer Aided Design systems are currently being used to drive machine vision analysis. Such an approach makes it possible to produce recognition and analysis procedures without having to scan a physical example of the object. Typically, these proposed techniques either directly use whatever the CAD model produces or derive information (e.g., points sampled on the surface of the object) to drive a particular recognition scheme. In this regard, there has been some discussion as to an appropriate set of interface data (e.g., points, surface patches, features, etc.). We propose that a coherent general solution to this problem is to characterize a CAD system by the set of intrinsic 3-D shape characteristics (e.g., surface normals, texture, reflectance properties, curvature, etc.) that the CAD system is able to provide. Such a characterization makes it possible to compare CAD systems irrespective of recognition paradigms, and actually makes it possible to determine which recognition strategies can be used with a given CAD-based machine vision system.