Contourlet Texture Retrieval with Energy and Kurtosis Features
[1]
Xinwu Chen, College of Physics and Electronics, Xinyang Normal University, Xinyang, China.
[2]
Jingjing Xue, College of Physics and Electronics, Xinyang Normal University, Xinyang, China.
[3]
Shuangbo Xie, College of Physics and Electronics, Xinyang Normal University, Xinyang, China.
[4]
Li Zhang, College of Physics and Electronics, Xinyang Normal University, Xinyang, China.
Contourlet is superior to wavelet at image denoising, texture image retrieval, and some other image application fields. This paper aims at improving the retrieval rate of contourlet retrieval system by using different features. We proved that the combination of energy and kurtosis can perform well incorporated with Canberra distance. Experimental results on 109 brodatz texture images showed that using the features cascaded by energy and kurtosis can lead to a higher retrieval rate than the combination of standard deviation and energy, and some other combinations which are most commonly used today under same dimension of feature vectors. Filter type and decomposition parameters can influence retrieval results.
Content Based Image Retrieval, Contourlet Transform, Texture Image Retrieval System, Energy, Kurtosis
[1]
SmeuldersA, Worring M, Santini S, etc. “Content-based image retrieval at the end of the early years”, IEEE Trans. Pattern Recognit. Machine intell., Vol 22, No. 12, pp. 1349–1380, Dec, 2000.
[2]
Minh N Do, Martin Vetterli. M, “Wavelet-based texture retrieval using Generalized Gaussian density and kullback-leibler distance”, IEEE transactions on image processing, Vol 11, No. 2, pp. 146-158, Feb. 2002.
[3]
Laine A, Fan J, “Texture classification by wavelet packet signatures”, IEEE trans. pattern recognit. machine intell., Vol 15, pp. 1186–1191, Nov. 1993.
[4]
Chang T, Kuo C, “Texture analysis and classification with tree-structure wavelet transform”, IEEE trans. onimage processing, Vol 2, pp. 429–441, Oct. 1993.
[5]
Smith J R, Chang S F, “Transform features for texture classification and discrimination in large image databases”, Proceedings of IEEE Int Conf. on Image Processing, Texas, pp. 407-411, November 1994.
[6]
Do, M N, Vetterli M. “Contourlets: a directional multiresolution image representation”, International Conference on Image Processing. New York, pp. 357-360, September, 2002.
[7]
Cunha D, Zhou J, Do M N, “The nonsubsampledcontourlet transform: theory, design, and applications”, IEEE transactions on image processing, Vol 15, pp. 3089 – 3101, Oct. 2006.
[8]
Lu Y, Do M N. “A new contourlet transform with sharp frequency localization”, Proceeding ofIEEE International Conference on Image Processing, Atlanta, pp. 8-11, Oct. 2006.
[9]
Qimin Cheng and Guangxi Zhu. “Contourlet spectral histogram for texture retrieval of remotely sensed imagery”. Proceeding of SPIE on Remote Sensing and GIS Data Processing and Other Applications, Yichang, pp. 74981R-74981R-6, October, 2009.
[10]
Arun K. S, Hema P Menon, “Content Based Medical Image Retrieval byCombining Rotation Invariant Contourlet Features and Fourier Descriptors”, International Journal of Recent Trends in Engineering, Vol 2, pp. 35-39, Nov. 2009.
[11]
Zhang Jinwen, Zhang Runpu, relative phase in dual tree shearlets [J], signal processing, 96(2014)241-252.
[12]
An Vo; Soontorn Oraintara. A study of relative phase in complex wavelet domain: Property, statistics and applications in texture image retrieval and segmentation[J], Signal Processing: image communication 25(2010)28-46.
[13]
Kokare M, Chatterji B N, Biswas P K. “Comparison of similarity metrics for texture image retrieval”, IEEE TENCON Conference, Bangalore, pp. 571-575, October, 2003.
[14]
Trygve R. “Brodatz texture images”, http://www.ux.uis.no/~tranden/brodatz.html, September, 2004.
