计算机科学 ›› 2016, Vol. 43 ›› Issue (1): 53-56.doi: 10.11896/j.issn.1002-137X.2016.01.012

• CRSSC-CWI-CGrC2015 • 上一篇    下一篇

基于曲率的全仿射曲线图像配准

柴先涛,梁久祯,稂龙亚   

  1. 江南大学物联网工程学院智能系统与网络计算研究所 无锡214122,江南大学物联网工程学院智能系统与网络计算研究所 无锡214122,江南大学物联网工程学院智能系统与网络计算研究所 无锡214122
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金(61202312,61170121)资助

Full Affine Curve in Curvature Scale Space Image Registration

CHAI Xian-tao, LIANG Jiu-zhen and LANG Long-ya   

  • Online:2018-12-01 Published:2018-12-01

摘要: 为了解决视点变化造成曲线图像匹配和识别困难的问题,利用全仿射模型建立仿射变换图库,在图库样本中通过曲率信息找出与目标样本相关性最优的样本,从而达到曲线图像匹配和识别的目的。基于曲率的全仿射曲线图像匹配的方法, 首先根据全仿射模型对样本图像建立样本库,对样本库中每一个样本通过等间隔偏移进行采样,然后对采样后的子样本建立曲率样本子集,将目标图像与样本子集中的每一个样本进行快速最近邻搜索算法相似性匹配;最后通过匹配结果,找到最优匹配样本。实验结果表明,基于曲率的全仿射曲线图像配准具有较高的成功率,并且与传统算法相比具有更多的优点。

关键词: 曲率,曲线匹配,全仿射模型,仿射不变

Abstract: To solve the problems that viewpoint change of curve image results in difficult matching and recognition,we used full affine transformation model library in the gallery to find the optimal sample correlated with the target by the curvature information,so as to achieve the matching and identification of curve image.In this paper,based on image matching method of curvature full affine curve, a sample library of sample images was established according to the full affine model.In a sample library,each sample is sampled by equal interval offset sampling.Then curvature subset of samples is established for the sub-samples.A fast nearest neighbor search algorithm is carried out using the target ima-ge and the sample subset for similarity matching.Finally the optimal matching sample is found by matching results.Experimental results show that the full affine curve image registration based on curvature has a high success rate,and has more advantages compared with traditional algorithms.

Key words: Curvature,Curve matching,Full affine model,Affine invariant

[1] Turk M A,Pentland A P.Eigenfaces for recognition[J].Journal of Cognitive Neuroscience,1991,3(1):71-86
[2] Chen Q,Defrise M,Deconinck F.Symmetric phase-only matched filtering of Fourier-Mellin transforms for image registration and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(12):1156-1168
[3] Li X M,Zhang J F.An Evaluation Method for Image Registration by Machine Learning[J].Acta Automatica Sinica,2008,4(1):7-13(in Chinese)李晓明,张继福.一种基于学习的自动图像配准检验方法[J].自动化学报,2008,4(1):7-13
[4] Sapiro G,Tannenbaum A.Affine invariant scale-space[J].Internatioal Journal of Computer Vision,1993,11(1):25-44
[5] Mokhtarian F,Mackworth A.Scale-based description and recognition of planar curves and two-dimensional shapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986(1):34-43
[6] Mokhtarian F,Abbasi S.Shape similarity retrieval under affine transforms[J].Pattern Recognition,2002,35(1):31-41
[7] He X C,Yung N H C.Curvature scale space corner detector with adaptive threshold and dynamic region of support [C]∥ Proceedings of the 17th IEEE International Conference on Pattern Recognition (ICPR’04).Aug 2004,2:791-794
[8] Cui M,Femiani J,Hu J,et al.Curve matching for open 2Dcurves[J].Pattern Recognition Letters,2009,30(1):1-10
[9] Lim K B,Du T H,Wang Q.Partially occluded object recognition[J].International Journal of Computer Applications in Techno-logy,2011,40(1):122-131
[10] Zhang Y S,Zou Z R.Automatic registration method for remote sensing images based on improved ORB algorithm [J].Remote Sensing for Land and Resources,2013,25(3):20-24(in Chinese)张云生,邹峥嵘.基于改进ORB算法的遥感图像自动配准方法[J].国土资源遥感,2013,25(3):20-24
[11] Yuan X G,Peng G H,Wang L.GPU-based Real Time ImageRegistration with Variant SIFT[J].Computer Science,2011,38(3):300-303(in Chinese)袁修国,彭国华,王琳.基于GPU的变型 SIFT算子实时图像配准[J].计算机科学,2011,38(3):300-303
[12] Morel J M,Yu G.ASIFT:A new framework for fully affine invariant image comparison[J].SIAM Journal on Imaging Sciences,2009,2(2):438-469
[13] Muja M,Lowe D G.Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration[C]∥Proc of the VISAPP International Conference on Computer Vision Theory and Applications.2009:331-340
[14] Kimia shape database [DB/OL].http://www.lems.Brown.edu/vision/ software/ index.html

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!