基于SURF特征和Delaunay三角网格的图像匹配

闫自庚; 蒋建国; 郭丹

doi:10.3724/SP.J.1004.2014.01216

基于SURF特征和Delaunay三角网格的图像匹配

doi: 10.3724/SP.J.1004.2014.01216

1.
合肥工业大学计算机与信息学院合肥 230009

基金项目:

国家自然科学基金（61272393，61172164，61174170），中央高校基本科研业务费专项资金（2013HGCH）资助

详细信息

作者简介:
蒋建国合肥工业大学计算机与信息学院教授. 主要研究方向为数字图像分析与处理，分布式智能系统和DSP 技术及应用. E-mail：jgjiang@hfut.edu.cn

计量
- 文章访问数: 2418
- HTML全文浏览量: 150
- PDF下载量: 1080
- 被引次数: 0
出版历程
- 收稿日期: 2013-04-02
- 修回日期: 2013-08-01
- 刊出日期: 2014-06-20

Image Matching Based on SURF Feature and Delaunay Triangular Meshes

1.
School of Computer and Information, Hefei University of Technology, Hefei 230009

Funds:

Supported by National Natural Science Foundation of China (61272393, 61172164, 61174170), and Chinese Universities Scientific Fund (2013HGCH)

摘要

摘要: 图像特征匹配的核心是通过距离函数实现在高维矢量空间进行相似性检索.重点研究提取好的特征点并快速准确地找到查询点的近邻.首先，提取图像的多量、有区别且稳健的SURF（Speeded up robust feature）特征点，并将特征点凸包进行Delaunay剖分.然后，对Delaunay三角边抽样、聚类、量化并构建索引.通过票决算法，将点对匹配与否映射到矩阵中以解决距离度量没有利用数据集本身所蕴含的任何结构信息和搜索效率相对较低的问题.结合SURF算法和Delaunay三角网提出一种特征匹配的新方法，在标准图像集上的实验验证，在耗时基本相同的情况下，提取的特征点较多且正确匹配率较高.
- SURF (Speeded up robust feature)特征 /
- Delaunay三角网格 /
- 点对 /
- 特征匹配
Abstract: The most important part in image feature matching is to retrieve feature vectors via a distance function. This paper focuses on better extracting feature points and establishing points' neighborhoods more quickly and accurately. First, the convex hulls of speeded up robust feature (SURF) feature points are divided into Delaunay triangles. Then, the indexes of the Delaunay connections are built by sampling, clustering and quantization. Finally, we construct a matching grid of the pairwise points by a voting algorithm, which improves matching efficiency without using any relevant structural information. The paper proposes a novel matching method based on SURF feature and Delaunay triangular meshes. Experiment results verify that, the method is able to extract more feature points and achieve feature matching with a higher accuracy while maintaining time cost.
- Speeded up robust feature (SURF) /
- Delaunay triangular meshes /
- pairwise points /
- feature matching

HTML全文

参考文献(18)

[1]	Wang M, Li H, Tao D C, Lu K, Wu X D. Multimodal graph-based reranking for web image search. IEEE Transactions on Image Processing, 2012, 21(11): 4649-4661
[2]	Wang M, Yang K Y, Hua X S, Zhang H J. Towards a relevant and diverse search of social images. IEEE Transactions on Multimedia, 2010, 12(8): 829-842
[3]	Bay H, Ess A, Tuytelaars T, van Gool L. Speeded-up robust features (SURF). Computer Vision and Image Understanding, 2008, 110(3): 346-359
[4]	Mikolajczyk K, Schmid C. A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630
[5]	Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110
[6]	Bauer J, Sünderhauf N, Protzel P. Comparing several implementations of two recently published feature detectors. In: Proceeding of the International Conference on Intelligent and Autonomous Systems. Toulouse, France: IAV, 2007. 1-6
[7]	Ooi B C, McDonell K J, Sacks-Davis R. Spatial Kd-tree: an indexing mechanism for spatial databases. In: Proceedings of the IEEE International Computers Software and Applications Conference. Tokyo: IEEE, 1987. 433-438
[8]	Weinberger K Q, Blitzer J, Saul L K. Distance metric learning for large margin nearest neighbor classification. Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2006
[9]	Chen J H, Chen C S, Chen Y S. Fast algorithm for robust template matching with M-estimators. IEEE Transactions on Signal Processing, 2003, 51(1): 230-243
[10]	Torr P H S, Zisserman A. MLESAC: a new robust estimator with application to estimating image geometry. Computer Vision and Image Understanding, 2000, 78(1): 138-156
[11]	Choi S, Kim T, Yu W. Performance evaluation of RANSAC family. In: Proceedings of the British Machine Vision Conference. London, UK: BMVC, 2009. 1-12
[12]	Tereshchenko V, Taran D. Optimal algorithm for constructing the Delaunay triangulation in E^d. In: Proceedings of World Academy of Science, Engineering and Technology. Turkey: World Academy of Science, 2012. 713-718
[13]	von Hundelshausen F, Sukthankar R. D-nets: beyond patch-based image descriptors. In: Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington, DC, USA: IEEE, 2012. 2941-2948
[14]	Wan Lin. Study on Image Representation Method Based on Triangular Mesh [Ph.D. dissertation], Huazhong University of Science and Technology, China, 2009. 15-42(万琳. 基于三角网格的图像表示方法研究 [博士学位论文], 华中科技大学, 中国, 2009. 15-42)
[15]	Yang S L, Chen M, Pomerleau D, Sukthankar R. Food recognition using statistics of pairwise local features. In: Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco, CA: IEEE, 2010, 2249-2256
[16]	Ashbrook A P, Thacker N A, Rockett P I, Brown C I. Robust recognition of scaled shapes using pairwise geometric histograms. In: Proceedings of the 6th British Conference on Machine Vision. Surrey, UK: BMVA Press, 1995. 503-512
[17]	Boyer R S, Moore J S. MJRTY—a fast majority vote algorithm. Automated Reasoning: Essays in Honor of Woody Bledsoe. Boston: Kluwer Academic Publishers, 1991. 105-118
[18]	Wang Yong-Ming. Image Local Invariant Features and Descriptors. Beijing: National Defence Industry Press, 2010, 89-100(王永明. 图像局部不变性特征与描述. 北京: 国防工业出版社, 2010. 89-100)