A Region-Based Image Matching Combining Global and Local Features

Jing Hou; Jin Xiang Pian; Ying Zhang; Ming Yue Wang

doi:10.4028/www.scientific.net/AMM.182-183.1868

Paper Titles

Relaxed Parallel Scheduling Algorithms Investigation of Support Resource Reservation from Grid
p.1849

Iterated Hybrid Localization Algorithm for Random Wireless Sensor Networks Based on Centroid and DV-Hop Algorithm
p.1854

Application of Different Algorithms to Predict the Faults and Fractures in Carbonate Formation
p.1858

Moving Object Detection Based on Edge Difference and Contour Matching
p.1863

A Region-Based Image Matching Combining Global and Local Features
p.1868

The Anti-Interference of the PLC Application System
p.1873

A Method of Improving Calculation Accuracy in Difference Schemes
p.1877

An Improved Spectral Clustering Algorithm Using Minimum Maximum Principle
p.1881

Study on Identification Algorithm of EEG Imaginary Movements
p.1885

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 182-183A Region-Based Image Matching Combining Global and...

A Region-Based Image Matching Combining Global and Local Features

Abstract:

A new approach is presented to match two images in presenting large scale changes. The novelty of our algorithm is a hierarchical matching strategy for global region features and local descriptors, which combines the descriptive power of global features and the discriminative power of local descriptors. To predict the likely location and scale of an object, global features extracted from the segmentation regions is used in the first stage for an efficient region matching. This initial matching can be ambiguous due to the instability and unreliability of global region feature, and therefore in the later stage local descriptors are matched within each region pair to discard false positives and the final matches are filtered by RANSAC. Experiments show the effectiveness and superiority of the proposed method in comparing to other approaches.

You might also be interested in these eBooks

Applied Mechanics and Mechatronics Automation

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 182-183)

Pages:

1868-1872

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.182-183.1868

Citation:

Cite this paper

Online since:

June 2012

Authors:

Jing Hou, Jin Xiang Pian, Ying Zhang, Ming Yue Wang

Keywords:

Affine-SIFT, Image Matching, RANSAC, Segmentation

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] K. Murphy, A. Torralba, D. Eaton, W. Freeman, in: Toward Category-Level Object Recognition, Springer Berlin / Heidelberg Publisher( 2006), pp.382-400.

DOI: 10.1007/11957959_20

Google Scholar

[2] D.G. Lowe, in: Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, vol. 1152 (1999), pp.1150-1157.

Google Scholar

[3] J. Matas, O. Chum, M. Urban, T. Pajdla, in: In British Machine Vision Conference (2002), pp.384-393.

Google Scholar

[4] A. Toshev, S. Jianbo, K. Daniilidis, in: Computer Vision and Pattern Recognition(2007), pp.1-8.

Google Scholar

[5] T. Cour, F. Benezit, J. Shi, in: Computer Vision and Pattern Recognition, vol. 1122(2005), pp.1124-1131.

Google Scholar

[6] E. Shechtman, M. Irani, in: Computer Vision and Pattern Recognition(2007), pp.1-8.

Google Scholar

[7] J.L. Shih, L.H. Chen, in: Vision, Image and Signal Processing, IEEE Proceedings, 149 (2002), pp.370-376.

Google Scholar

[8] J.M. Morel, G. Yu, in: SIAM Journal on Imaging Sciences, 2 (2009), pp.438-469.

Google Scholar

[9] M. Fischler, R. Bolles, in: Commun. ACM, 24 (1981), pp.381-395.

Google Scholar

[10] L. Fei-Fei, P. Perona, in: Computer Vision and Pattern Recognition, vol. 522 (2005), pp.524-531.

Google Scholar