基于径向曲线与支持向量回归的颅骨修复

doi:10.19678/j.issn.1000-3428.0059839

摘要/Abstract

摘要： 颅骨修复技术是对有缺损的颅骨补全对应的缺损部分，进而实现颅骨形状的完整性。针对高维颅骨数据，本文采用径向曲线来表示颅骨几何特征，结合最小二乘支持向量回归的方法构建颅骨修复模型。首先，提取完整的三维颅骨模型的径向曲线，将其分为已有径向曲线和缺失径向曲线两部分作为训练样本；然后采用最小二乘支持向量回归(LSSVR)统计模型复原出待修复颅骨的缺失径向曲线，进而合并生成待修复颅骨的完整径向曲线；最后，通过迭代最近点（ICP）算法将合并的颅骨径向曲线与颅骨统计模型进行匹配生成完整的三维颅骨模型。在 190 套颅骨数据上进行修复结果对比，该方法的平均误差达到 6.834×10 -3 ，比主成分分析( PCA)方法提高了 2.90 倍，实验结果证明该方法具有更好的修复效果。

Abstract: The skull restoration technology is to restore the missing part of the defected skull to complete the skull shape. For high-dimensional skull data, radial curves are used to represent the skull geometry features in this paper, a skull restoration model is constructed by combining with the method of least square support vector regression. First, the radial curves of the complete three-dimensional skull model are extracted as training data, which is divided into two parts: the existed radial curves and the defective radial curves; Then the least squares support vector regression (LSSVR) statistical model is used to restore the defective radial curve of the skull to be repaired. Next, they are combined into a set of radial curves of the skull; Finally, the iterative closest point (ICP) algorithm is used to match the generated skull radial curve with the skull statistical model to generate a complete three-dimensional skull model. Compared the restored results on 190 sets of skull data, the average error of our method was 6.834×10 -3 , which was 2.90 times higher than that of Principal Component Analysis (PCA) method. The experimental results proved that this method had a better repair effect.

陈仲晗 , 赵俊莉 , 黄瑞坤. 基于径向曲线与支持向量回归的颅骨修复[J]. 计算机工程, doi: 10.19678/j.issn.1000-3428.0059839.

CHEN Zhonghan , ZHAO Junli , HUANG Ruikun. Skull Restoration Based on Radial Curve and Support Vector Regression[J]. Computer Engineering, doi: 10.19678/j.issn.1000-3428.0059839.

参考文献

[1] Yang Rong, Feng Youqian, Yuan Xiujiu. Using existing models to repair incomplete 3D models[J]. Journal of Computer Aided Design and Graphics, 2015(01): 98-105. (in Chinese) 杨荣, 冯有前, 袁修久. 利用现有模型修复不完整三维模型[J]. 计算机辅助设计与图形学学报, 2015(01): 98-105.
[2] Bao Jiarui, Liang Ronghua, Wu Fuli, et al. Complicated hole repair of 3-dimensional skull surface model[J]. Journal of Image and Graphics,2013,18(9): 1156-1163. (in Chinese) 包佳蕊,梁荣华,吴福理, 等. 3 维颅骨表面模型的复杂孔洞修补[J].中国图象图形学报,2013,18(9): 1156-1163.
[3] Davis J, Marschner S, Garr M, Levoy M. Filling holes in complex surfaces using volumetric diffusion ［C］ // The First International Symposium on 3D Data. Padua, Italy: IEEE, 2002: 428-438.
[4] Nooruddin F S, Turk G. Simplification and Repair of Polygonal Models using Volumetric Techniques[J]. IEEE Transactions on Visualization and Computer Graphics, 2003, 9(2): 191-205.
[5] Ju T. Robust Repair of Polygonal Models[J]. ACM Transactions on Graphics, 2004, 23(3): 888-895.
[6] Centin M, Pezzotto N, Signoroni A. Poisson-driven seamless completion of triangular meshes[J]. Computer Aided Geometric Design, 2015, 35-36(may): 42-55
[7] Lin Hongbin, Wang Wei. Feature preserving holes filling of scattered point cloud based on tensor voting[C]//IEEE International Conference on Signal & Image Processing. IEEE, 2017.
[8] Liepa P. Filling Holes in Meshes[C]// Proceedings of the 2003 Eurographics/ACM SIGGRAPH symposium on Geometry processing. Switzerland: Eurographics Association, 2003: 200-205.
[9] Jun Y. A piecewise Hole Filling Algorithm in Reverse Engineering[J]. Computer-Aided Design, 2005, 37(2): 263-270.
[10] Zhao W, Gan S, Lin H. A robust Hole-filling Algorithm for Triangular Mesh[J]. The Visual Computer, 2007, 23(12): 987-997.
[11] Li Yuewen, Geng Guohua, Wei Xiaoran. A Hole Repair Algorithm Based on Poisson Equation[J]. Computer Engineering, 2017, 43(10): 209-215,221. 李月雯,耿国华,魏潇然.基于泊松方程的孔洞修补算法[J]. 计算机工程,2017,43(10): 209-215,221.
[12] Wang L C, Hung Y C. Hole filling of triangular mesh segments using systematic grey prediction[J]. Computer-Aided Design, 2012, 44(12): 1182-1189.
[13] Quinsat Y, Lartigue C. Filling holes in digitized point cloud using a morphing-based approach to preserve volume characteristics[J]. International Journal of Advanced Manufacturing Technology, 2015, 81(1-4): 411-421.
[14] Wu Xiaojing, Shou Huahao, Shao Maozhen. Repairing triangle mesh holes with inner normal vector and quadratic error metric [J]. Journal of Computer Aided Design and Graphics, 2020, 32(2): 239-245. (in Chinese) 吴晓婧,寿华好,邵茂真.用内法向量与二次误差度量修补三角网格孔洞 [J]. 计算机辅助设计与图形学学报,2020,32(2): 239-245.
[15] Wen Peizhi, Lei Yongqing, Sun Menglong. Defect and hole identification and repair method of 3D reconstruction mesh model[J]. Application Research of Computers, 2020, 37(4): 1234-1238. (in Chinese) 温佩芝, 雷永庆, 孙梦龙. 三维重建网格模型的缺陷孔洞识别与修复方法[J].计算机应用研究, 2020, 37(4): 1234-1238.
[16] GENG Guohua, DENG Qingqiong, ZHAO Wanrong, et al. A method of repairing 3D skull loss based on multiple cases[J]. Journal of System Simulation, 2016, 28(10): 2335-2341. (in Chinese) 耿国华, 邓擎琼, 赵万荣等. 一种基于多样例的三维颅骨缺失修补方法 [J]. 系统仿真学报 , 2016, 28(10):2335-2341.
[17] He Y, Gao N, Ru S, et al. A local modeling approach of craniofacial shape correlation based on PLSR[C]// 2017 2nd International Conference on Image, Vision and Computing. IEEE, 2017.
[18] Wang Lin, Zhao Junli, Duan Fuqing, et al. Overview of craniofacial restoration methods[J]. Computer Engineering, 2019, 45(12): 8-18. (in Chinese) 王琳,赵俊莉,段福庆, 等.颅面复原方法综述[J]. 计算机工程, 2019, 45(12): 8-18.
[19] Junli Zhao, XinQi, Chengfeng Wen, et al. Automatic and Robust Skull Registration based on Discrete Uniformization[C]//International Conference on Computer Vision 2019, IEEE, 2019.10.27-2019.11.
[20] Xin Zheng, Junli Zhao*, Zhihan Lv, et al. Skull similarity comparison based on SPCA[J]. Multimedia Tools and Applications (2020): 1-24.
[21] Junli Zhao, Zhenkuan Pan, Fuqing Duan, et al. A Survey on 3D Face Recognition based on Geodesics [J]. Journal of Information Hiding and Multimedia Signal Processing, 2019, 10(2): 368-386
[22] Zhao J L, Wu Z K, Pan Z K, et al. 3D Face Similarity Measure by Fréchet Distances of Geodesics[J]. Journal of Computer Science & Technology, 2018, 33(1): 207-222.
[23] Ying Xiang, Huang Caibao, Fu Xuzhou, et al. Parallelizing discrete geodesic algorithms with perfect efficiency[J]. Computer-Aided Design, 2019, 115: 161-171.
[24] Wang X, Fang Z, Wu J, et al. Discrete geodesic graph (DGG) for computing geodesic distances on polyhedral surfaces[J]. Computer Aided Geometric Design, 2017, 52(MAR.-APR.): 262-284.
[25] Huang R, Zhao J, Duan F, et al. Automatic craniofacial registration based on radial curves[J]. Computers & Graphics, 2019, 82: 264-274.
[26] Wang S, Han Z, Liu F, et al. Nonlinear system identification using least squares support vector machine tuned by an adaptive particle swarm optimization[J]. International Journal of Machine Learning & Cybernetics, 2015, 6(6): 981-992.
[27] Yan Li, Liang Chang, Xuejun Qiao, et al. Craniofacial reconstruction based on least square support vector regression[C]//IEEE International Conference on Systems, Man, and Cybernetics (SMC), San Diego, CA, USA: IEEE. 2014: 1147-1151.
[28] Facchinei F, Kanzow C, Sagratella S. Solving quasi-variational inequalities via their KKT conditions[J]. Mathematical Programming, 2014, 144(1-2): 369-412.
[29] Berar M, Desvignes M, Gérard Bailly, et al. 3D Semi-Landmarks Based Statistical Face Reconstruction[J]. Journal of Computing & Information Technology, 2006, 14(1): 31-43.