一种非刚性三维模型的尺度不变局部特征提取方法

Scale-Invariant Local Feature Extraction Method for Non-Rigid 3D Model

提出了一种具有尺度不变性的非刚性三维模型局部特征提取方法,即基于局部多值模式的热核特征(local multilevel pattern based heat kernel signatures,LMP-HKS).首先设计了一种适用于一维信号的基于局部多值模式的编码方法;然后通过对HKS特征的对数差分结果使用局部多值模式来计算特征直方图向量,以获得局部特征向量.该特征不仅保留了HKS特征的等距不变性、信息完备性及稳定性等优良特性,而且具有尺度不变性.与同样具有尺度不变性的SI-HKS特征相比,LMP-HKS特征对于非刚性三维模型的局部形状结构具有更强的描述能力.大量非刚性三维模型检索的实验结果验证了该局部特征的有效性.

In this paper,a novel scale-invariant local feature extraction method was presented for nonrigid 3 D model,called LMP-HKS（local multilevel pattern based heat kernel signatures）.Firstly,a coding method was designed based on the local multilevel pattern to describe 1 D（one dimension）signal suitably.Then the feature histogram was computed with local multilevel pattern to describe the logarithm difference of the heat kernel signatures.Analyses results show that,the proposed method can not only retain the excellent characteristics of HKS feature,such as isometric invariance,completeness and stability et al,but also keep the local feature scale invariant.Compared with SI-HKS feature that is also scale invariant,the LMP-HKS feature shows better descriptive ability for local shape structure of the 3 Dnon-rigid model.The effectiveness of the proposed local feature has been validated by extensive non-rigid 3 Dmodel retrieval experiments.