Manufacturing companies often need to reuse existing design information to reduce cost and timeto-market. This requires search tools that are capable of locating previously designed parts. Many geometry-based search techniques have been developed to locate parts similar to the input query part. But these techniques are not effective if the user does not have a query part to provide as input to the geometry-based search system. This paper describes an integrated search system for searching a part database both visually and geometrically for locating and retrieving parts. The visual and geometry-based search tools of this integrated system are highly interconnected and provide a seamless transition between either modes of searching. The visual search tool uses levelof-detail techniques to display a large number of parts in the scene. It has multiple navigation and sorting utilities to search the database visually. The geometry-based search tool uses gross-shape based search techniques to provide effective searching capabilities. The system described in this paper has been tested with a wide variety of parts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.