Matching 3D models with global geometric feature map

Measuring the similarity between 3D models is a fundamental task in 3D models retrieval. In this paper, we propose a new method based on global geometric feature map (GGFM) to represent arbitrary polygonal 3D models. Since 3D polygonal model can be expressed as a set of facets, the GGFM can fast constitute a spherical histogram about the normal orientation and area and position of every facet on the surface of the model. By computing the spherical correlation between the GGFMs of the matched models, similarity of two models can be obtained. Experimental results show that the proposed method performs well in 3D model similarity matching and is invariant to the translation and rotation and scaling of 3D model. Comparing to the existing methods, this method is fast and needs low computation and storage cost since each facet of the model needs to be computed only once in GGFM