Content-based 3D object retrieval on VRML database

VRML is rapidly becoming the standard file format for delivery of 3D contents across the Internet. Most 2D, even 3D content-based retrieval techniques are designed based on 2-D information such as shape or texture comparison. In this paper, we propose a new similarity method, based on 3D information extracted from a VRML object database. User may give a VRML object, and find VRML scenes that use the similar object via our system. The system includes multiple subsystems, which will be conducted in two main parts. First part includes: the VRML objects parser system and the normalization system. The second part: includes the comparison system, database management system and a friendly graphical user interface. Besides, the feedback learning mechanism enhances the precision of retrieval. The experience shows that the system is able to retrieve 3D objects from VRML database with high satisfactorily.