期刊文献+

基于薄膜振动模型的曲线匹配方法 被引量:1

A New Curve Matching Method Based on Membrane Vibration Model
下载PDF
导出
摘要 提出了一种基于薄膜振动模型的仿射不变曲线描述子.本文针对两种类型的曲线匹配进行研究:若尔当曲线和开曲线.对于若尔当曲线,首先将若尔当曲线进行标准化,消除仿射畸变对曲线匹配的影响,然后应用有限元方法在标准化曲线的区域内求解Helmholtz方程的本征值构造曲线描述子;对于开曲线,首先应用欧氏距离变换对开曲线建立窄带模型形成封闭区域,然后提取窄带的若尔当曲线代替原开曲线,最后利用若尔当曲线匹配的方法提取曲线描述子,实现开曲线的匹配.用图像库中的图像和真实图像进行实验,结果表明本文方法要优于现有的傅里叶形状描述方法和Zernike矩描述方法. A novel affine invariant curve descriptor based on membrane vibration model is proposed in this paper. This paper focused on two kinds of curves,of which one is Jardon curve and the other is open curve.For the Jardon curve,it was firstly nor- malized to overcome the influence of affime distortion. The curve descriptors were then obtained by calculating the eigenvalues of Helmholtz equation using the finite element method;For the open curve,its narrowband model region was firstly established by use of Euclidean distance transform. Then the open curves were replaced by the narrowband models. Finally the open curve descriptors were obtained by using the Jardon curve' s method. The experimental results show that the proposed method outperforms the existing Fourier descriptor and Zernike moment descriptor.
出处 《电子学报》 EI CAS CSCD 北大核心 2013年第10期1917-1925,共9页 Acta Electronica Sinica
基金 国家自然科学基金(No.61063030) 国家973重点基础研究发展计划(No.2009CB320902) 江西省自然科学基金(No.2010GZS0168) 江西省科技支撑计划项目(No.2009BGA00800) 江西省教育厅科技项目(No.GJJ11512)
关键词 曲线匹配 薄膜振动 若尔当曲线 HELMHOLTZ方程 窄带模型 curve matching membrane vibration Jardon curves Helmholtz equation narrowband model
  • 相关文献

参考文献19

  • 1Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts [ J ]. IEEE Transactions on Pattern Analysis and Machine InteUigence,2002,24(4) :509 - 522.
  • 2吕玉增,彭启民,黎湘.基于极值特征的不变性形状识别[J].电子学报,2008,36(4):679-684. 被引量:10
  • 3Zhang D S, Lu G. Review of shape representation and descrip- tion techniques[ J] .Pattern Recognition, 2004,37( 1 ) : 1 - 19.
  • 4Abbasi S, Mokhtarian F, Kittler J. Curvature scale space image in shape sinul' arity retrieval [ J ]. Multimedia Systems, 1999, 7 (6) :467 - 476.
  • 5Persoon E, Fu K. Shape discrimination using fourier descriptors [J].IEEE. Transon SMC, 1977,7(3) :170- 179.
  • 6Zhang D, Lu G. A comparative study of curvature scale space and fourier descriptors for shape-based image retrieval [ J ]. Journal of Visual Communication and Image Representation,2002, 14( 1 ) : 39 - 57.
  • 7Ekombo P L E, Ennahnahi N, Oumsis M, Meknassi M. Appli- cation of affine invariant fourier descriptor to shape-based im- age retrieval[ J] .International Journal of Computer Science and Network Security,2009,9(7) :240 - 247.
  • 8王斌.一种不变的基于傅立叶变换的区域形状描述子[J].电子学报,2012,40(1):84-88. 被引量:13
  • 9Flusser J, Suk T. Pattern recognition by aft'me moment invari- ants[ J]. Pattern Recognition, 1993,26(1) : 167 - 174.
  • 10Teague M R. Image analysis via the general theory of mo- ments[ J]. Journal of the Optical Society of America, 1979,70 (8) :920 - 930.

二级参考文献28

  • 1Berretti S, A. Bimbo D, Pala P. Retrieval by shape similarity with perceptual distance and effective indexing. Content-based image retrieval at the end of the early years[ J]. IEEE Trans on Multimedia, 2(4) :225 - 239,2000.
  • 2Kirn W Y, Kim Y S. A region-based shape descriptor using Zemike moments [J].Signal Processing: Image Communica- tion,2000,16( 1 - 2) :95 - 102.
  • 3Lu G J, Sajjanhar A. Region-based shape representation and similarity measure suitable for content-based image retrieval [J] .Multimedia Systems, 1999,7(2) :165 - 174.
  • 4Persoon E, Fu K. Shape discrimination using Fourier descriptors [J]. IEEE Trans on SMC, 1977,7(3):170- 179.
  • 5Gonzalez R C,Woods R E.Digital Image Processing[M] .Ad- dison-Wesley. Reading, MA, 2002.655 - 659.
  • 6Urdiales C, Bandera A, Sandoval F. Non-parametric planar shape representation based on adaptive curvature functions[ J]. Pattern Recolmition, 2002,35 ( 1 ) : 45 - 53.
  • 7Kauppinen H, Seppanen T, Pietikainen M. An experimental comparison of autoregressive and Fourier-based descriptors in 2D shape classification[ J].IEEE Trans Pattern Anal Mach In- tell, 1995,17(2) :201 - 207.
  • 8Zhang D S, Lu G J. Study and evaluation of different Fourier methods for image retrieval[J].Image and Vision Computing, 2005,23(1) :33 - 49.
  • 9Mehtre B M, Kankanhalli M S, Lee W F. Shape measure for content based image retrieval: A comparison[J]. Information Processing & Management, 1997,33(3) : 319 - 337.
  • 10Zhang D S,Lu G J. Shape-based image retrieval using generic Fourier descriptor[ J ]. Signal PIxxessing: Image Communica- tion, 2002,17(10) :825 - 848.

共引文献26

同被引文献6

引证文献1

二级引证文献6

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