Contourlet-1.3 Texture Retrieval Using Absolute Mean Energy and Kurtosis Features

Abstract:

To improve the texture image retrieval rate of contourlet texture image retrieval system, a contourlet-1.3 transform based texture image retrieval system was proposed. In the system, the contourlet transform was contourlet-1.3, a new version of the original contourlet, sub-bands absolute mean energy and kurtosis in each contourlet-1.3 sub-band were cascaded to form feature vectors, and the similarity metric was Canberra distance. Experimental results on 109 brodatz texture images show that using the features cascaded by absolute mean energy and kurtosis can lead to a higher retrieval rate than the combination of standard deviation and absolute mean energy which is most commonly used today under same dimension of feature vectors. Contourlet-1.3 transform based image retrieval system is superior to those of the original contourlet, non-subsampled contourlet and contourlet-2.3 systems under same system structure with same dimension of feature vectors, retrieval time and memory needed.

• Periodical: Applied Mechanics and Materials (Volumes 48-49)
• Pages: 327-330
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.48-49.327
• Online since: February 2011
• Authors: Xin Wu Chen, Li Wei Liu
• Keywords: Content Based Image Retrieval, Contourlet Transform, Contourlet-1.3 Transform, Contourlet-2.3 Transform, Non-Subsampled Contourlet Transform, Retrieval Rate, Texture Image

References

[1] Minh N D, Vetterli M, in: Wavelet-Based Texture Retrieval Using Generalized Gaussian Density and Kullback-Leibler Distance. IEEE Transactions On Image Processing, 2002, 11(2): 146-158.

DOI: 10.1109/83.982822

[2] Laine A, Fan J, in: Texture Classification by Wavelet Packet Signatures. IEEE Trans. Pattern Recognit. Machine Intell., 1993, 15(11): 1186–1191.

DOI: 10.1109/34.244679

[3] Do M N, Vetterli M, in: Contourlets: A Directional Multiresolution Image Representation. International Conference on Image Processing. 2002: 357-360.

DOI: 10.1109/icip.2002.1038034

[4] Cunha D, Zhou J, in: Do M.N. The Nonsubsampled Contourlet Transform: Theory, Design, and Applications. IEEE Transactions on Image Processing, 2006, 15(10): 3089 – 3101.

DOI: 10.1109/tip.2006.877507

[5] Lu Y, Do M N, in: A New Contourlet Transform with Sharp Frequency Localization. Proceeding of IEEE International Conference on Image Processing, 2006: 8-11.

DOI: 10.1109/icip.2006.312657

[6] Arun K S, Hema P M, in: Content Based Medical Image Retrieval by Combining Rotation Invariant Contourlet Features and Fourier Descriptors. International Journal of Recent Trends in Engineering, 2009, 2(2): 35-39.

[7] Kokare M, Chatterji B N, Biswas P K, In: Comparison of Similarity Metrics for Texture Image Retrieval. IEEE TENCON Conference, 2003: 571-575.

DOI: 10.1109/tencon.2003.1273228

[8] Trygve R, in: Brodatz Texture Images. http: /www. ux. uis. no/~tranden/ brodatz. html.