Abstract
We apply the complex wavelet structural similarity index to image matching system and propose an image matching method which has strong robustness to image transform in spatial domain. Experimental results show that the structural similarity index in complex wavelet domain reflects to a large extent structural similarity of the images compared, which is more similar to human visual cognitive system; in the meanwhile, because of approximate shift invariance of complex wavelet, this index shows good robustness to such disturbance as contrast ratio change and illumination change to template image, so it is more suitable to be used as similarity index for image matching under complex imaging conditions. Moreover, matching simulation experiment shows that this method has higher correct matching rate in complicated disturbance environment.
Sponsored by the National Natural Science Foundation (60873192).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Sun, Z.-k., Shen, Z.-k.: Digital image processing and its application. National Defence Industry Press, Bei**g (1985)
Zitova, B., Flusser, J.: Image registration methodspp. A survey. Image and Vision Computing 21, 977–1000 (2003)
Brown, L.G.: A survey of Image registration techniques. ACM Computing Surveys 24, 325–376 (1992)
Li, H.-s., Xu, D.-x., Xu, G.-s.: A image matching algorithm based on complex–valued wavelet transform. Systerms Engineering and Electronics 24, 83–86 (2002)
Huttenlocher, D.O., Klanderman, G.A., Rucklidge, W.J.: Comparing images using the Hausdorff Distance. IEEE Trans. on Pattern Analysis and Machine Intelligence 15, 850–863 (1993)
Wang, Z., Bovik, A.C., Sheikh, H.R., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing 13, 600–612 (2004)
Zhao, W.-f., Shen, H.-b., Yan, X.-l.: Structural similarity measurement based on dual-tree complex wavelet. Journal of Zhejiang University (Engineering Science) 42, 1385–1388 (2008)
Mehul, P.S., Wang, Z., Shalini, G., et al.: Complex wavelet structural similarity: a new image similarity index. IEEE Transactions on Image Processing 18, 2385–2401 (2009)
Kingsbury, N.G.: The dual-tree complex wavelet transformpp. a new technique for shift invariance and directional filters. In: Proceedings of 8th IEEE DSP Workshop, pp. 86–89. IEEE, Bryce Canyon (1998)
Kingsbury, N.G.: Complex wavelets for shift invariant analysis and filtering of signals. Applied Computational Harmonic Analysis 10, 234–253 (2001)
Kingsbury, N.G.: A dual-tree complex wavelet trans-form with improved orthogonality and symmetry properties. In: Proceedings of IEEE Conference on Image Processing, pp. 375–378. IEEE, Los Alamitos (2000)
Kingsbury, N.G.: Design of q-shift complex wavelets for image processing using frequency domain energy minimization. In: Proceedings of IEEE International Conference on Image Processing, pp. 1013–1016. IEEE, Barcelona (2003)
Wang, Z., Simoncelli, E.P.: Translation insensitive image similarity in complex wavelet domain. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 573–576. IEEE, Philadelphia (2005)
Quan, W., Wang, X.-d., Gan, J.: Comparison and analysis of similar measure in image matching. Aeronautical Computing Technique 38, 18–20 (2008)
Gan, J., Wang, X., Quan, W.: A fast image matching algorithm based on characteristic points. Electronics Optics & Control 16 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
An, J., Zhang, X. (2011). Robust Image Matching Method Based on Complex Wavelet Structural Similarity. In: Lin, S., Huang, X. (eds) Advances in Computer Science, Environment, Ecoinformatics, and Education. CSEE 2011. Communications in Computer and Information Science, vol 215. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23324-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-23324-1_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23323-4
Online ISBN: 978-3-642-23324-1
eBook Packages: Computer ScienceComputer Science (R0)