一种基于多样例的三维颅骨缺失修补方法

系统仿真学报 ›› 2016, Vol. 28 ›› Issue (10): 2335-2341.

一种基于多样例的三维颅骨缺失修补方法

热孜万古丽·夏米西丁^1,2, 耿国华^1,*, 古丽松·那斯尔丁², 邓擎琼³, 迪丽努尔·克依木², 祖丽皮亚·买买提明², 赵万荣⁴, 郑磊⁴

1.西北大学信息科学与技术学院,西安 710069;
2.新疆师范大学计算机科学技术学院,乌鲁木齐 830054;
3.北京师范大学信息科学与技术学院,北京 100875;
4.托克逊县人民医院放射科,新疆吐鲁番 838100

收稿日期:2016-05-20 修回日期:2016-07-14 出版日期:2016-10-08 发布日期:2020-08-13
作者简介:热孜万古丽·夏米西丁(1968-),女,维吾尔族,新疆托克逊县,博士生,讲师,研究方向为颅面形态学。
基金资助:
国家自然科学基金(61363065,61262065); 北京市自然科学基金(4152028)

3D Skull Surface Completion Method Based on Multi-exemplars

Reziwanguli Xiamixiding^1,2, Geng Guohua¹, Gulisong Nasierding², Deng Qingqiong³, Dilinuer Keyimu², Zulipiya Maimaitiming², Zhao Wanrong⁴, Zheng Lei⁴

1. School of Information and Technology, Northwest University, Xi'an, 710069, China;
2. College of Computer Science and Technology, Xinjiang Normal University, Urumchi 830054, China;
3. College of Information Science and Technology, Beijing Normal University, Beijing 100875, China;
4. Department of Radiology, Peoples Hospital of Toksun, Turpan Xinjiang 838100, China

Received:2016-05-20 Revised:2016-07-14 Online:2016-10-08 Published:2020-08-13

摘要/Abstract

摘要： 针对刑侦及考古中的遗骨经常存在缺损的问题,提出一种基于多样例的三维颅骨缺失修补方法。构建三维颅骨样本库,并通过配准算法对所有样本进行规格化处理;利用同样的配准算法根据待修补颅骨的缺失情况把样本库中的每个样本对应地分为存留和缺失两部分数据;通过回归算法获得两部分数据之间的函数关系;利用该函数关系计算待修补颅骨的缺失数据,并通过拼接融合得到最终的结果。实验结果表明,该方法能有效修补大、小缺失,同时保留原模型的所有特征;此外,避免了现有基于样例方法带个性特征的缺陷,修补误差更小。

关键词: 三维模型修补, 多样例, 颅骨, 回归

Abstract: In order to repair the damaged skulls, a skull completion method based on multiple exemplars was proposed. A 3D skull model database was constructed, and all the exemplars within the database were registered with a standard skull model. Each exemplar was then divided into a missing part and a remaining part according to the given damaged skull. After that, the relationship between the missing part and the remaining part was obtained by a regression algorithm. This relationship was used to calculate the missing part of the given skull, and a complete skull could be obtained by merging the two parts. Experimental results demonstrate that the proposed method can repair small and large damages well while keep the original model unchanged. In addition, it can improve the completion accuracy compared with the existing example-based methods.

Key words: 3D model completion, multi-exemplar, skull, regression

中图分类号:

TP399

热孜万古丽·夏米西丁, 耿国华, 古丽松·那斯尔丁, 邓擎琼, 迪丽努尔·克依木, 祖丽皮亚·买买提明, 赵万荣, 郑磊. 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.

Reziwanguli Xiamixiding, Geng Guohua, Gulisong Nasierding, Deng Qingqiong, Dilinuer Keyimu, Zulipiya Maimaitiming, Zhao Wanrong, Zheng Lei. 3D Skull Surface Completion Method Based on Multi-exemplars[J]. Journal of System Simulation, 2016, 28(10): 2335-2341.

参考文献 17

[1]	Attene M, Campen M, Kobbelt L.Polygon Mesh Repairing: an Application Perspective[J]. ACM Comput. Surv.(S0360-0300), 2013, 45(2): 15.
[2]	Liepa P.Filling Holes in Meshes[C]// Proceedings of the 2003Eurographics/ACM SIGGRAPH symposium on Geometry processing. Switzerland: Eurographics Association, 2003: 200-205.
[3]	Pernot J P, Moraru G, Véron P.Filling Holes in Meshes using a Mechanical Model to Simulate the Curvature Variation Minimization[J]. Computers & Graphics (S0097-8493), 2006, 30(6): 892-902.
[4]	刘咏梅, 李凤霞, 雷正朝, 等. 基于边界特征增长的孔洞修补算法[J]. 系统仿真学报, 2014, 26(9): 1916-1921.
[5]	Davis J, Marschner S R, Garr M, et al.Filling Holes in complex Surfaces using Volumetric Diffusion[C]// Proceedings, First International Symposium on 3D Data Processing Visualization and Transmission. USA: IEEE, 2002: 428-441.
[6]	Hétroy F, Rey S, Andújar C, et al.Mesh Repair with user-friendly Topology Control[J]. Computer-Aided Design (S0010-4485), 2011, 43(1): 101-113.
[7]	Harary G, Tal A, Grinspun E.Context-based Coherent Surface Completion[J]. ACM Trans. Graph (S0730-0301), 2014, 33(1): 5.
[8]	Sharf A, Alexa M, Cohen-Or D.Context-based Surface Completion[J]. ACM Trans. Graph (S0730-0301), 2004, 23(3): 878-887.
[9]	Park S, Guo X, Shin H, et al.Shape and Appearance Repair for Incomplete Point Surfaces[C]// Tenth IEEE International Conference on Computer Vision, vol.2. Beijing, USA. USA: IEEE, 2005:1260-1267.
[10]	Pauly M, Mitra N J, Giesen J, et al. Example-based 3d Scan Completion [C]// Proc. Third Eurographics symposium on Geometry processing, SGP ’05, Switzerland: Eurographics Association, 2005, Article No. 23.
[11]	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, 27(1): 98-105.
[12]	Sahay P, Rajagopalan A N.Harnessing Self-similarity for Reconstruction of Large Missing Regions in 3d Models[C]// Processing ICPR, Tsukuba, Japan. USA: IEEE, 2012: 101-104.
[13]	Sahay P, Rajagopalan A N.Geometric Inpainting of 3D Structures[C]// Proc. 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Boston, MA, USA. USA: IEEE, 2015: 1-7.
[14]	Q Deng, M Zhou, W Shui, et al.A Novel Skull Registration based on Global and Local Deformations for Craniofacial Reconstruction[J]. Forensic Science International (S0379-0738). 2011, 208(1-3): 95-102.
[15]	Sahillioglu Y, Yemez Y.Coarse-to-Fine Combinatorial Matching for Dense Isometric Shape Correspondence[J]. ?Computer Graphics Forum (S1467-8659). 2011, 30(5): 1461-1470.
[16]	Kovnatsky A, Bronstein M M, Bresson X, et al. Functional Correspondence by Matrix Completion[C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA. USA: IEEE, 2015: 905-914.
[17]	Zhang S, Zhan Y, Metaxas D N.Deformable Segmentation via Sparse Representation and Dictionary Learning[J]. Medical Image Analysis (S1361-8415). 2012, 16(7): 1385-96.