基于参数化的三维颅面配准

计算机应用 ›› 2014, Vol. 34 ›› Issue (12): 3589-3592.

基于参数化的三维颅面配准

乔学军¹,²,赵俊莉²,³,⁴,鲁健庆²,³,谢文魁³

1. 西安建筑科技大学理学院,西安 710055
2. 虚拟现实应用教育部工程研究中心，北京 100875
3. 北京师范大学信息科学与技术学院,北京100875
4. 青岛大学软件技术学院,山东青岛 266061

收稿日期:2014-06-27 修回日期:2014-09-16 出版日期:2014-12-01 发布日期:2014-12-31
通讯作者: 赵俊莉
作者简介:乔学军(1970-),男,陕西西安人,副教授,硕士,主要研究方向:计算机图形学；赵俊莉(1977-),女,山西新绛人,讲师,博士研究生,主要研究方向:虚拟现实与可视化；鲁健庆(1988-),男, 山东潍坊人,硕士研究生,主要研究方向:信号与信息处理；谢文魁(1987-),男,江西吉安人,硕士,主要研究方向:计算机图形学。
基金资助:
国家自然科学基金重点项目;中央高校基本科研业务费专项基金资助项目

3D craniofacial registration using parameterization

QIAO Xuejun¹,²,ZHAO Junli¹,³,⁴,LU Jianqing¹,³,XIE Wenkui³

1. Engineering Research Center of Virtual Reality and Applications Ministry of Education (MOE), Beijing 100875, China
2. School of Science, Xi'an University of Architecture and Technology, Xi'an Shaanxi 710055, China;
3. College of Information Science and Technology, Beijing Normal University, Beijing 100875, China;
4. College of Software and Technology, Qingdao University, Qingdao Shandong 266061, China;

Received:2014-06-27 Revised:2014-09-16 Online:2014-12-01 Published:2014-12-31
Contact: ZHAO Junli

摘要/Abstract

摘要：

针对颅面配准问题,提出通过对颅面进行参数化将其转换成二维参数域的对应问题。首先,根据人类的生理特征标定6个特征点,利用这些特征点将颅面转换到一个统一的坐标系以实现姿态和大小的统一；其次,以两个外眼角为约束对参考颅面进行最小二乘保角映射,计算出6个特征点的参数值；然后,以这六个生理特征点的参数值为约束,利用最小二乘保角映射将任一待配准模型映射到二维参数域；最后,根据二维参数域确定三维颅面上的对应点,从而实现三维数据配准。为了验证所提方法,以对应点为控制点,利用薄板样条(TPS)变换把参考颅面变形到目标颅面,以变形后两个模型上对应点之间的几何距离的平均为度量,将所提算法和基于主轴分析的迭代最近点(ICP)配准以及基于随机采样控制点的迭代TPS配准方法进行了比较,实验结果表明,所提算法的配准效果优于其他两种方法。

Abstract:

This paper transfered the problem of the 3D craniofacial registration into the one in 2D parameter domain by using surface parameterization. Firstly, six landmarks on the craniofacial surfaces were calibrated according to the physiological characteristics, and the pose and size of the craniofacial surfaces were normalized by projecting the craniofacial surfaces into a unified coordinate system which was determined by using the six landmarks. Secondly, Least Squares Conformal Mapping (LSCM) was performed for a reference craniofacial surface by pinning two outer corners of the eyes, by which the 2D parameters of the six landmarks were computed. Thirdly, any craniofacial surface could be mapped into a 2D domain using LSCM by pinning the six landmarks. Finally, the 3D point correspondences were obtained by mapping the 2D correspondences into the 3D surfaces. To validate the proposed method, the reference model was deformed into the target one by the Thin Plate Spline (TPS) transform with the corresponding vertices being control points, and the average distance between two corresponding point sets after deformation was computed. By the average distance, the proposed method was compared with the principal axes analysis based ICP (Iterative Closest Point) and the random sampling control points based iterative TPS registration methods. The comparison shows that the proposed approach is more accurate and effective.

中图分类号:

TP301.6

乔学军赵俊莉鲁健庆谢文魁. 基于参数化的三维颅面配准[J]. 计算机应用, 2014, 34(12): 3589-3592.

QIAO Xuejun ZHAO Junli LU Jianqing XIE Wenkui. 3D craniofacial registration using parameterization[J]. Journal of Computer Applications, 2014, 34(12): 3589-3592.

参考文献

［1］SIDOROV K. Groupwise non-rigid registration for automatic construction of appearance models of the human craniofacial complex for analysis, synthesis and simulation［D］. Cardiff: University of Cardiff, 2009.
［2］ZENG Y, WANG C, WANG Y, et al. Dense non-rigid surface registration using high-order graph matching［C］// Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2010: 382-389.
［3］HU Y, DUAN F, YIN B, et al. A hierarchical dense deformable model for 3D face reconstruction from skull［J］. Multimedia Tools and Applications, 2013, 64(2): 345-364.
［4］DENG Q, ZHOU M, SHUI W, et al. A novel skull registration based on global and local deformations for craniofacial reconstruction［J］. Forensic Science International, 2011, 208(1): 95-102.
［5］BESL P J, MCKAY N D. Method for registration of 3D shapes［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256.
［6］YANG J, LI H, JIA Y. Go-ICP: Solving 3D registration efficiently and globally optimally［C］// Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway: IEEE,2013:1-8.
［7］RUSINKIEWICZ S, LEVOY M. Efficient variants of the ICP algorithm［C］// Proceedings of the 3rd International Conference on 3-D Digital Imaging and Modeling. Piscataway: IEEE, 2001: 145-152.
［8］LI S, WANG P, SHEN Z. A survey of iterative closest point algorithm［J］. Signal Processing,2009, 2(10):1582-1588.(李世飞, 王平, 沈振康. 迭代最近点算法研究进展［J］. 信号处理, 2009, 25(10): 1582-1588.)
［9］ZHANG G, ZHANG Y, GUO Z. 3D face registration based on accurate principal axes analysis and ICP［J］. Computer Engineering and Applications, 2006, 42(29):62-64.(张广鹏, 张艳宁, 郭哲. 基于精确主轴分析及 ICP 的三维人脸配准［J］. 计算机工程与应用, 2006, 42(29): 62-64.)
［10］GUO Y, ZHANG H, WANG J, et al. An improved distance threshold constrainted ICP algorithm for 3D registration［J］. Journal of China Academy of Electronics and Information Technology,2012,6(6):643-647.(郭琰, 张会林, 王金伟, 等. 基于改进距离阈值约束的ICP三维配准方法［J］. 中国电子科学研究院学报, 2012, 6(6): 643-647.)
［11］ZHANG X, LI Z, WANG X, et al. Research of 3D point cloud data registration algorithms based on feature points and improved ICP［J］. Transducer and Microsystem Technologies,2012,31(9):116-118.(张晓娟, 李忠科, 王先泽,等. 基于特征点和改进 ICP的三维点云数据配准算法［J］. 传感器与微系统, 2012, 31(9): 116-118.)
［12］HUTTON T J, BUXTON B F, HAMMOND P. Automated registration of 3D faces using dense surface models［C］// Proceedings of the 2003 British Machine Vision Conference. Malvern: British Machine Vision Association, 2003: 439-448.
［13］BOOKSTEIN F L. Principal warps: Thin-plate splines and the decomposition of deformations［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(6): 567-585.
［14］BROWN B J, RUSINKIEWICZ S. Non-rigid range-scan alignment using thin-plate splines［C］// Proceedings of the 2nd International Symposium on 3D Data Processing, Visualization and Transmission. Washington, DC: IEEE Computer Society,2004: 759-765.
［15］SCHNEIDER D C, EISERT P, HERDER J, et al. Algorithms for automatic and robust registration of 3D head scans［J］. Journal of Virtual Reality and Broadcasting, 2010, 7(7): 1-15.
［16］HU Y, ZHOU M, WU Z. A dense point-to-point alignment method for realistic 3D face morphing and animation ［J］. International Journal of Computer Games Technology, 2009, 2009(3):1-9.
［17］HAKER S, ANGENENT S, TANNENBAUM A R, et al. Conformal surface parameterization for texture mapping［J］. IEEE Transactions on Visualization and Computer Graphics, 2000,6(2):181-189.
［18］WANG S, WANG Y, JIN M, et al. Conformal geometry and its applications on 3D shape matching, recognition, and stitching［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(7): 1209-1220.
［19］LVY B, PETITJEAN S, RAY N, et al. Least squares conformal maps for automatic texture atlas generation［J］. Proceedings of the 2002 ACM Transactions on Graphics, 2002, 21(3): 362-371.
［20］ISO/IEC. JTCI/SC29/WGll Document N390［EB/OL］.［2014-02-20］. http://infoscience.epfl.ch/record/86498/files/Ebrahimi1997_428.pdf.

[1]	肖智豪胡志华朱琳. 求解冷链物流时间依赖型车辆路径问题的混合自适应大邻域搜索算法[J]. 计算机应用, 0, (): 0-0.
[2]	沙林秀，聂凡，高倩，孟号. 基于布朗运动与梯度信息的交替优化算法[J]. 计算机应用, 0, (): 0-0.
[3]	董永峰孙跃华高立超韩鹏季海鹏. 基于改进一维卷积和双向长短期记忆神经网络的故障诊断方法[J]. 计算机应用, 0, (): 0-0.
[4]	李大海刘庆腾艾志刚王振东. 基于动态D向分割和混沌扰动的阴阳对算法[J]. 计算机应用, 0, (): 0-0.
[5]	雷鹰郑万波魏嵬夏云霓李晓波刘诚武谢洪. 基于概率性能感知演化博弈策略的混合“云+边”环境中任务卸载方法 [J]. 计算机应用, 0, (): 0-0.
[6]	乔钢柱王瑞孙超利. 基于分解的高维多目标改进进化算法[J]. 计算机应用, 0, (): 0-0.
[7]	朱诚潘旭华张勇. 基于趋化校正的哈里斯鹰优化算法[J]. 计算机应用, 0, (): 0-0.
[8]	平凡汤小春潘彦宇李战怀. 不规则任务在图形处理器集群上的调度策略[J]. 计算机应用, 0, (): 0-0.
[9]	杨杰张名扬芮晓彬王志晓. 融合节点覆盖范围和结构洞的影响力最大化算法[J]. 计算机应用, 0, (): 0-0.
[10]	汤安迪, 韩统, 徐登武, 谢磊. 混沌精英哈里斯鹰优化算法[J]. 计算机应用, 2021, 41(8): 2265-2272.
[11]	李蒙蒙, 秦伟, 刘艺, 刁兴春. 结合头脑风暴优化的混合蚁群优化算法[J]. 计算机应用, 2021, 41(8): 2412-2417.
[12]	张闻强, 邢征, 杨卫东. 基于多区域采样策略的混合粒子群优化求解多目标柔性作业车间调度问题[J]. 计算机应用, 2021, 41(8): 2249-2257.
[13]	张祥飞, 鲁宇明, 张平生. 基于协同进化的约束多目标优化算法[J]. 计算机应用, 2021, 41(7): 2012-2018.
[14]	张萌, 李维华. 用户互动表示下的影响力最大化算法[J]. 计算机应用, 2021, 41(7): 1964-1969.
[15]	王宇, 刘燕丽, 陈劭武. 基于顶点冲突学习的最大公共子图算法[J]. 计算机应用, 2021, 41(6): 1756-1760.