您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(理学版)》

山东大学学报(理学版) ›› 2014, Vol. 49 ›› Issue (12): 43-48.doi: 10.6040/j.issn.1671-9352.3.2014.124

• 论文 • 上一篇    下一篇

基于曲率尺度空间的轮廓线匹配方法

靳永刚, 王凡, 胡小鹏   

  1. 大连理工大学计算机科学与技术学院, 辽宁 大连 116024
  • 收稿日期:2014-08-28 修回日期:2014-10-17 出版日期:2014-12-20 发布日期:2014-12-20
  • 作者简介:靳永刚(1989- ),男,硕士研究生,研究方向为模式识别与机器视觉. E-mail:hkj_c4@163.com
  • 基金资助:
    国家自然科学基金资助项目(61272523)

Contour matching method based on curvature scale space

JIN Yong-gang, WANG Fan, HU Xiao-peng   

  1. School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, Liaoning, China
  • Received:2014-08-28 Revised:2014-10-17 Online:2014-12-20 Published:2014-12-20

摘要: 基于曲率尺度空间(curvature scale space, CSS)理论,提出了一种匹配和识别存在仿射变化的平面曲线的方法。首先借助边缘检测算法提取图像轮廓,利用PCA白化算法消除轮廓线尺度、平移和切变的影响;然后对轮廓进行重采样并求取对应曲率尺度空间图的局部极值点;最后利用局部极值点向量数组作为轮廓线的描述符进行匹配。在MCD形状数据库的对比检索实验结果表明本文所提出的方法不仅有较高的检索率,而且对仿射变化具有良好的鲁棒性。

关键词: 图像配准, 曲率尺度空间, 轮廓线匹配, PCA白化

Abstract: An approach for matching and recognizing affine-distorted planar shapes was proposed, which is based on the theory of curvature scale space (CSS). First, the contours were extracted by edge detection algorithm, and then use the PCA whitening method to eliminate the impact of scale, translation and shear. Second, the contour was resampled and the local maximum point was extracted. Final, the array of points was used as descriptor to match. The proposed method was evaluated on MCD shape database, and the experimental results show that the method not only has the higher retrieval ratio but also is robust to affine transformation.

Key words: image registration, curvature scale space, PCA whitening, contour match

中图分类号: 

  • TP391
[1] EL-GHAZAL A, BASIR O, BELKASIM S. Invariant curvature-based fourier shape descriptors[J]. Journal of Visual Communication and Image Representation, 2012, 23(4):622-633.
[2] 王斌. 一种基于多尺度拱高形状描述的图像检索方法[J].电子学报,2013, 41(9):1821-1825. WANG Bin. Image retrieval using multi-scale arch height shape description[J]. Acta Electronica Sinica, 2013, 41(9):1821-1825.
[3] GIANNEKOU V, TZOUVELI P, AVRITHIS Y, et al. Affine invariant curve matching using normalization and curvature scale-space[J]. Proceedings of International Workshop on Content-Based Multimedia Indexing(CBMI 2008), 2008: 208-215.
[4] HUANG Zhaohui, COHEN F S. Affine-invariant B-Spline moments for curve matching[J]. Image Processing, 1996, 5(10):1473-1480.
[5] ZHAO Dongming, CHEN Jie. Affine curve moment invariants for shape recognition[J]. Pattern Recognition, 1997, 30(6):895-901.
[6] ZHANG Dengsheng, LU Guojun. Shape-based image retrieval using generic Fourier descriptor[J]. Signal Processing, 2002, 17(10):825-848.
[7] WANG Yue, TEOH E K. 2D Affine-invariant contour matching using B-Spline model[J]. Pattern Analysis and Machine Intelligence, 2007, 29(10):1853-1858.
[8] MOKHTARIAN F, ABBASI S, JOSEF K. Efficient and robust retrieval by shape content through curvature scale space[C]// Proceedings of International Workshop on Image Databases and Multimedia Search.[S.l.]:[s.n.], 1996: 35-42.
[9] MAI F, CHANG C Q, HUNG Y S. Affine-invariant shape matching and recognition under partial occlusion [C]// Proceedings of 2010 17th IEEE International Conference on Image Processing (ICIP). New York: IEEE, 2010: 4605-4608.
[10] LAKEHAL A, BEQQALI O E, ZEMZAMI O A. Retrieval of similar shapes under affine transform using affine length parameterization[J]. Journal of Computer Science, 2010, 6(10):1226-1232.
[11] ZULIANI M, BHAGAVATHY S, MANJUNATH B S. Affine-invariant curve matching[J]. Image Processing, 2004, 5:2041-3044.
[12] SENER S, MUSTAFA U. A new affine invariant curve normalization technique using independent component analysis[J]. Pattern Recognition, 2006, 2:48.
[13] BOBER M, PRETEUX F, KIM W Y. Introduction to MPEG-7: multimedia content description interface[M]. New York: John Wiley & Sons, Inc, 2002.
[1] 常晓丽 李金屏. 一种新的多模态图像集成配准方法[J]. J4, 2009, 44(9): 35-39.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!