3D model retrieval using distribution of interpolated normal vectors on simplified mesh

This paper proposes the direction distribution of surface normal vectors as a feature descriptor of three-dimensional models. Rotation invariance required as a feature descriptor is handled using principal component analysis(PCA) method, and mesh simplification is performed to make it robust and nonsensitive against noise addition. Samples are picked up for distribution of normal vectors to be proportional to the area of each polygon, weight is applied to the normal vectors, and interpolation is applied to enhance discrimination so that the information on the surface with less area may be less reflected on composing a feature descriptor. Similarity between models is measured with a L1-norm in the probability density histogram where the distances of feature descriptors are normalized. It was verified that the proposed method has improved the retrieval performance described in an average normalized modified retrieval rank(ANMRR) by about 17.2% and the retrieval performance described in a quantitative discrimination scale by 9.6%~17.5% as compared to the existing method.