期刊文献+

基于SURF特征与边缘信息的图像配准 被引量:5

Image Registration Based on SURF Features and Edge Information
下载PDF
导出
摘要 目的:针对特征图像配准方法速度快、效率高,而医学图像具有结构信息不明显、变形复杂等特点,该类方法常常失效,提出一种结合SURF特征与图像边缘信息的配准方案。方法:首先使用SURF法检测图像的特征点,采用角度法判断特征点是否匹配错误,并将误匹配的特征点删除;然后,将所得特征点对与图像的Canny边缘相结合,形成一个新的特征点集;最后使用TPS-RPM法对该特征点集进行配准。结果:采用边缘点与SURF特征结合的配准方案,减少了特征点误匹配产生的不良影响,提出的筛选特征点方法能有效地删除部分匹配错误的特征点对。结论:该方案比只用SURF特征匹配的结果更为精确。 Objective: For the fast and high efficiency of image registration methods for features,they often fail in medical image registration because the structural information of medical images are not obvious and the deformation of medical images is always complex,a method combined SURF features and edge information is presented for image registration.Methods: First,the SURF is used for features detection.Then the mismatched points are found and deleted according to the angles between features.Next,the obtained feature point couples are combined with Canny edge to construct a new set for feature points.Finally,the TPS-RPM method is used to conduct image registration for the feature points set.Results: The image registration method that combines the edge points and the SURF features can reduce the error caused by feature points mismatching,and the proposed feature points selecting method can partly delete the mismatched feature point couples effectively.Conclusions: The proposed image registration method is more effective than the SURF image registration method.
出处 《中国医学物理学杂志》 CSCD 2011年第6期3000-3003,3024,共5页 Chinese Journal of Medical Physics
基金 国家自然科学基金资助项目(No.61172184) 中国博士后科学基金特别资助项目(No.200902482)
关键词 图像配准 SURF Canny边缘 image registration SURF canny edge
  • 相关文献

参考文献11

  • 1金英.优化的CT图像配准方法的研究与比较[J].黑龙江大学工程学报,2011,2(1):93-99. 被引量:2
  • 2戴修斌,张辉,舒华忠,罗立民.基于正交矩混合不变量的离焦模糊图像配准信号与信息处理[J].应用科学学报,2010,28(5):476-484. 被引量:2
  • 3张明慧,卢振泰,冯前进.利用局部区域约束的医学图像弹性配准[J].计算机工程与应用,2010,46(20):119-121. 被引量:5
  • 4David G. Lowe.Distinctive Image Features from Scale-Invariant Keypoints[J]. International Journal of Computer Vision . 2004 (2)
  • 5Bay H,,Ess A,Tuytelaars T.Speeded-Up Robust Features(SURF). Computer Vision and Image Understanding . 2008
  • 6Chui H,Rangarajan A.A new point matching algorithm for non-rigid registration. Computer Vision and Image Understanding . 2003
  • 7Barbara Zitova,Jan Flusser.Image registration methods: a survey. Image and Vision Computing . 2003
  • 8Lowe D.Object Recognition from Local Scale-Invariant Features. Proceedings of the International Conference on Computer Vision . 1999
  • 9Ke Y,Sukthankar R.PCA-SIFT:A more distinctive representation for local image descriptors. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . 2004
  • 10Mikolajczyk K,Schmid C.Indexing based on scale invariant interest points. Proceedings of the 8th IEEE International Conference on Computer Vision . 2001

二级参考文献37

  • 1冯林,张名举,贺明峰,戚正君,滕弘飞.用分层互信息和薄板样条实现医学图像弹性自动配准[J].计算机辅助设计与图形学学报,2005,17(7):1492-1496. 被引量:16
  • 2马义德,钱志柏,陈娜.基于FCM的动态结合全局图像阈值分割[J].电子科技大学学报,2006,35(3):349-351. 被引量:4
  • 3黄永锋,李杉,赵俊.基于外标记点的2D/3D图像配准方法[J].上海交通大学学报,2006,40(7):1108-1111. 被引量:3
  • 4Zitova B,Flusser J.Image registration methods:A survey[J].Image and Vision Computing,2003,21:977-1000.
  • 5Pluim J P W,Maintz J B A,Viergever M A.Mutual information based registration of medical images:A survey[J].IEEE Trans Medical Imaging,2003,23(6):1-21.
  • 6Camara O.Non-linear registration of thoracic and abdominal CT and 18-FDG whole-body emission PET images:Methodological study and application in clinical routine[D].Ecole Nationale Supérieure des Télécommunications,Paris,France,2003.
  • 7Frangi A F,Rueckert D,Schnabel J A,et al.Automatic construction of multiple-object three-dimensional statistical shape models:Application to cardiac modeling[J].IEEE Trans Med Imaging,2002,21:1151-1165.
  • 8Little J A,Hill D L G,Hawkes D J.Deformations incorporating rigid structures[J].Comput Vision Image Understand,1997,66:223-232.
  • 9Tanner C,Schnabel J A,Chung D,et al.Volume and shape preservation of enhancing lesions when applying non-rigid registration to a time series of contrast enhancing MR breast images[J].Lecture Notes in Computer Science,2000,1935:327-337.
  • 10Rohlfing T,Jr Maurer C R,Bluemke D,et al.Volume-preserving nonrigid registration of MR breast images using free-form deformation with an incompressibility constraint[J].IEEE Trans Med Imaging,2003,22:730-741.

共引文献5

同被引文献37

  • 1赵宏伟,刘宇琦,程禹,刘君玲.基于相位相关的图像匹配算法[J].吉林大学学报(工学版),2011,41(S1):183-188. 被引量:2
  • 2刘卫光,郭师红,周利华.红外与可见光图像实时配准融合系统[J].红外技术,2004,26(5):66-71. 被引量:14
  • 3王成儒,赵娜,张丽丽.基于三角形几何相似性的图像配准与拼接[J].光电工程,2007,34(8):87-92. 被引量:9
  • 4Jignesh N S, Suprava P. Automatic image registration using mexican hat wavelet, invariant moment, and randon transform[J]. International Journal of Advanced Computer Sciences and Application, 2011, Special: 75-$3.
  • 5Zhang H X, Zhang Y N, Guo Z. 3D face recognition based on principal axes registration and fusing features[J]. Fronties of Eleetrical and Electronic Engineering in China, 2011, 6(2): 347-352.
  • 6Jacub B, Jan F. 3D rigid registration by cylindrical phase correlation method[J]. Pattern Recognition Letters, 2009, 30: 914-921.
  • 7商会超.印刷图像在线检测的算法研究与系统实现[D].武汉:华中科技大学,2006.
  • 8CarstenS,MarkusU,ChristianW.机器视觉算法与应用.双语版[M].北京:清华大学出版社,2008.
  • 9Joan B R, Joan S A. JPEG2000 ROI coding through component priority for digital mammography [J]. Computer Vision and Image Understanding, 2011, 115: 59-68.
  • 10Cheng Y H, Han X W. Base on SIFT - Harris operator of the docu- ment image matching method [ C ]//Natural Resources and Sustain- able Development Ⅱ. Part 4,2012:3870 -3874.

引证文献5

二级引证文献7

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部