3D Shape Retrieval Method based on Normal-Angle Histogram

Authors

Lijun Jiang, School of Mechatronics Engineering, Harbin Institute of Technology, Harbin 150001, ChinaFollow

Author Country (or Countries)

China

Abstract

This paper puts forward 3D model retrieval method based on normal-angle histogram. The method firstly makes the pretreatment for 3D model, and defines the calculation method of the normal at every vertex of the triangular mesh in 3D model and the included angle among the triangular meshes. Then it classifies the triangular mesh in accordance with the normal at three vertexes of the triangular mesh and the included angle among the triangular meshes, and divides the triangular mesh into four types as per the included angle whether acute angle or obtuse angle, constructs the shape distribution curve for every type of triangular mesh collection, obtains the similarity of two shapes by comparison of four shape distribution curves of 3D model, and accordingly realizes the similarity retrieval of 3D model. The test indicates that the retrieval accuracy rate and the retrieval efficiency of the algorithm are superior to other similar histogram algorithm.

Recommended Citation

Jiang, Lijun (2015) "3D Shape Retrieval Method based on Normal-Angle Histogram," Applied Mathematics & Information Sciences: Vol. 09: Iss. 2, Article 59.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol09/iss2/59