通信学报 ›› 2013, Vol. 34 ›› Issue (5): 192-199.doi: 10.3969/j.issn.1000-436x.2013.05.022

• 学术通信 • 上一篇    下一篇

基于PDE的自适应鲁向异性图像配准方法研究

蒋淑静1,2,3,黑保琴3,张九星3,李倩男4   

  1. 1 中国科学院 光电研究院,北京 100094;
    2 中国科学院 研究生院,北京 100080;
    3 中国科学院 空间应用工程与技术中心,北京 100094
    4 解放军信息工程大学 密码工程学院,河南 郑州 450004
  • 出版日期:2013-05-25 发布日期:2017-06-27
  • 基金资助:
    载人航天工程民用试应用数据处理基金资助项目

Research on PDE-based adaptive anisotropic image registration

Shu-jing JIANG1,2,3,Bao-qin HEI3,Jiu-xing ZHANG3,Qian-nan LI4   

  1. 1 Academy of Optoelectronics,Chinese Academy of Sciences,Beijing 100094,China;
    2 Graduate University of Chinese Academy of Sciences,Beijing 100080,China;
    3 Technology and Engineering Center for Space Utilization,Chinese Academy of Sciences,Beijing 100094,China;
    4 Cryptography Engineering College of the PLA Information Engineering University,Zhengzhou 450004,China
  • Online:2013-05-25 Published:2017-06-27
  • Supported by:
    Civil Trial Data Processing Application of the Manned Space Fight Project

摘要:

摘要:针对传统光流场配准模型会造成图像模糊和细节丢失的问题,提出了一种基于偏微分方程的自适应各向异性配准模型。新模型将具有自适应性的扩散滤波方法引入图像配准,定义具有图像结构保持能力的各向异性扩散函数作为模型的正则项;数据项采用作用于亮度常量假设的非二次惩罚函数以增加模型的稳健性。实验结果表明,新模型能够有效保持图像特征,实现对大脑等复杂图像的有效配准。

关键词: 光流场, 图像配准, 自适应, 各向异性, 边缘对齐度

Abstract:

A PDE-based adaptive anisotropic model for image registration was proposed to solve the problem that tradi-tional optical flow brings on the image blurring and details losing.The new model introduces adaptivity image registration,and defines anisotropic diffusion function with the ability of preserving image structure as the regu-larization term;the data term use a non-quadratic penalty function with the assumption in brightness constant to improve the robust of the model.The experimental results show that the model can efficiently protect the image structure and achieve accurate registration of the complex image like brain.

Key words: optical flow, image registration, adaptive, anisotropic, edge alignment

No Suggested Reading articles found!