Characterizing 3D Shapes: A Complex Network-Based Approach

In the past few years, 3D models have emerged as the focus of many new applications. This recent popularity of 3D models has stimulated researchers to investigate the problems of 3D shape retrieval and to develop more efficient search and retrieval methods. Aiming to contribute to the recent literature, this work proposes a novel 3D shape characterization method using the complex network theory. By modeling a 3D shape object as a complex network we are able to effectively represent, characterize and analyze the object is terms of the topological properties of the complex network. Comparison with two other known methods for 3D model description, shape histograms and shape distributions, on a 3D models data set shows that the proposed technique is a feasible approach to efficiently perform 3D shape characterization and discrimination.