Journal of Computer Applications ›› 2016, Vol. 36 ›› Issue (11): 3196-3200.DOI: 10.11772/j.issn.1001-9081.2016.11.3196

Previous Articles     Next Articles

Automatic nonrigid registration method for 3D skulls based on boundary correspondence

Reziwanguli XIAMXIDING1,2, GENG Guohua1, Gulisong NASIERDING2, DENG Qingqiong3, Dilinuer KEYIMU2, Zulipiya MAIMAITIMING2, ZHAO Wanrong4, ZHENG Lei4   

  1. 1. School of Information Science and Technology, Northwest University, Xi'an Shaanxi 710069, China;
    2. College of Computer Science and Technology, Xinjiang Normal University, Urumqi Xinjiang 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:2016-04-15 Revised:2016-07-08 Online:2016-11-10 Published:2016-11-12
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61363065,61262065), Beijing Natural Science Foundation(4152028), the Fundamental Research Funds for the Central Universities (2013YB70).

基于边缘对应的三维颅骨自动非刚性配准方法

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. 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
  • 通讯作者: 耿国华
  • 作者简介:热孜万古丽·夏米西丁(1968-),女,新疆托克逊人,讲师,博士研究生,主要研究方向:颅面形态学、智能信息处理;耿国华(1955-),女,山东莱西人,教授,博士,CCF会员,主要研究方向:三维重建、智能信息处理、文化遗产数字化保护;古丽松·那斯尔丁(1961-),女,新疆玛纳斯人,副教授,博士,主要研究方向:数据挖掘、模式识别;邓擎琼(1981-),女,湖南郴州人,讲师,博士,CCF会员,主要研究方向:计算机图形学、颅面形态学;迪丽努尔·克依木(1977-),女,新疆伊犁人,讲师,硕士,主要研究方向:计算机程序设计;祖丽皮亚·买买提明(1974-),女,新疆乌鲁木齐人,讲师,硕士,主要研究方向:自然语言处理;赵万荣(1973-),男,新疆托克逊人,主治医生,主要研究方向:医学成像、影像诊断;郑磊(1978-),男,新疆托克逊人,主治医生,主要研究方向:影像诊断。
  • 基金资助:
    国家自然科学基金资助项目(61363065,61262065);北京市自然科学基金资助项目(4152028);中央高校基本科研业务费专项基金资助项目(2013YB70)。

Abstract: In order to automatically register the skulls that differ a lot in pose with the reference skull, or miss a large part of bones, an automatic nonrigid 3D skull registration method based on boundary correspondence was proposed. First, all the boundaries of target skull were calculated, and according to the edge length and the shortest distance between the edges, the edge type was identified automatically, and the correspondence between the registered skull and the reference skull was established. Based on that, the initial position and attitude of the skull were adjusted to realize the coarse registration. Finally, Coherent Point Drift (CPD) algorithm was used twice to realize the accurate registration of two skulls from the edge region to all regions. The experimental results show that, compared with the automatic registration method based on Iterative Closest Point (ICP) and Thin Plate Spline (TPS), the proposed method has stronger robustness in pose, position, resolution and defect, and has more availability.

Key words: 3D model registration, 3D skull, boundary recognition, coherent point drift, pose normalization

摘要: 针对三维颅骨模型在初始姿态相差较大以及存在较多缺失情况下自动配准困难的问题,提出一种基于边缘对应的三维颅骨非刚性自动配准方法。首先对待配准三维颅骨进行边缘提取,获得所有孔洞的边缘;然后根据边缘长度以及边缘间最短距离自动识别边缘类型,建立待配准颅骨和参考颅骨在边缘上的对应;之后对待配准颅骨的初始位置和姿态进行调整,实现粗配准;最后通过两次一致点漂移(CPD)算法逐步实现两个颅骨从边缘区域至所有区域的精确配准。实验结果表明,与常用的基于迭代最近点(ICP)和薄板样条函数(TPS)相结合的三维颅骨自动配准方法相比,该方法对姿态、位置、分辨率以及缺损具有更强的鲁棒性,并且配准效率更高。

关键词: 三维模型配准, 三维颅骨, 边缘识别, 一致点漂移, 姿态校正

CLC Number: