Structure correspondence searching of CAD model using local feature-based description and indexing

The CAD model retrieval has played a significant role in various applications, including product development and knowledge mining. However, most existing retrieval methods compare 3D shape similarity from a global perspective, while detecting similar structures automatically for CAD models remains a challenging problem. Consequently, this study proposes a structure correspondence searching framework for CAD models to address the issues. According to the boundary representation (B-rep) information, the proposed method first segments a CAD model into a set of local features denoted as structural cells. Then, the descriptor of each structural cell is extracted using a weighted shape distribution vector and neighbor set. In order to speed up the matching of structural cells, an indexing and filtering mechanism is constructed based on the shape clustering and topological analysis. The matched structural cells determine the boundary of similar structures. Finally, similarity measurement is conducted to generate a ranking list by analyzing the quality of the matched structural cells. The rationality and efficiency of the proposed approach are demonstrated via an analysis of experimental results.