论文信息 - Method for Comparative Analysis of Bullet Marks Based on the Multi-dimensional Feature Extraction

Method for Comparative Analysis of Bullet Marks Based on the Multi-dimensional Feature Extraction

This paper presents the method for comparative analysis of 3D bullet mark data and proposes the technology of realizing accurate comparative analysis by extracting multidimensional features of bullet data. In our approach, the first step is to denoise the data, and then extract multidimensional feature, finally we make the comparison of coarse level to fine level. The experimental results demonstrate the effectiveness of the method.

Gang Wu | Changjiang Song | Fengjiao Gao | Xindi Li

[1] Martial Hebert,et al. Parts-based 3D object classification , 2004, CVPR 2004.

[2] Szymon Rusinkiewicz,et al. Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors , 2003, Symposium on Geometry Processing.

[3] Lora Mak,et al. An extension of spherical harmonics to region-based rotationally invariant descriptors for molecular shape description and comparison. , 2008, Journal of molecular graphics & modelling.

[4] Janet M. Thornton,et al. Real spherical harmonic expansion coefficients as 3D shape descriptors for protein binding pocket and ligand comparisons , 2005, Bioinform..

[5] Jun Cheng,et al. Size Detection of Firebricks Based on Machine Vision Technology , 2010, 2010 International Conference on Measuring Technology and Mechatronics Automation.

[6] Carlo Ferrari,et al. Exploring the potential of 3D Zernike descriptors and SVM for protein–protein interface prediction , 2018, BMC Bioinformatics.