Shape Similarity Matching With Octree Representations
Shape matching is one of the fundamental problems in content-based 3D shape retrieval. Since there are typically a large number of possible matches in a shape database, there is a crucial need to perform shape matching efficiently. As a result, shapes must be reduced into a simpler shape representation, and computational complexity is one of the most important criteria for evaluating 3D shape representations. To meet the need, the investigators have implemented a new effective and efficient approach for 3D shape matching, which uses a simplified octree representation of 3D mesh models. The simplified octree representation was developed to improve time and space efficiency over prior representations. In addition, octree representations are rapidly becoming the standard file format for delivering 3D content across the Internet. The proposed approach stores octree information in XML files, rather than using a new data file type, to facilitate comparing models over the Internet. New methods for normalizing models, generating octrees, and comparing models were developed. The proposed approach allows users to efficiently exchange shape information and compare models over the Internet, in standardized data and data file formats, without transferring exact model files. The proposed approach is the first step in a project which will build a complete 3D model database and data retrieval system, which can be incorporated with other data mining techniques.