Using shape distributions to compare solid models

Abstract

Our recent work has described how to use feature and topology information to compare 3-D solid models. In this work we describe a new method to compare solid models based on shape distributions. Shape distribution functions are common in the computer graphics and computer vision communities. The typical use of shape distributions is to compare 2-D objects, such as those obtained from imaging devices (cameras and other computer vision equipment). Recent work has applied shape distribution metrics for comparison of approximate models found in the graphics community, such as polygonal meshes, faceted representation, and Virtual Reality Modeling Language (VRML) models. This paper examines how to adapt these techniques to comparison of 3-D solid models, such as those produced by commercial CAD systems. We provide a brief review of shape matching with distribution functions and present an approach to matching solid models. First, we show how to extend basic distribution-based techniques to handle CAD data that has been exported to VRML format. These extensions address specific geometries that occur in mechanical CAD data. Second, we describe how to use shape distributions to directly interrogate solid models. Lastly, we show how these techniques can be put together to provide a "query by example" interface to a large, heterogeneous, CAD database: The National Design Repository. One significant contribution of our work is the systematic technique for performing consistent, engineering content-based comparisons of CAD models produced by different CAD systems.