Use of Contourlets for Image Retrieval
We propose a simple technique for content-based image retrieval (CBIR) using contourlets that possess not only the multi-resolution time frequency localization properties of wavelets but are also good at capturing the directional information. Statistical features extracted from contourlet coefficients on each subband of the decomposed image, capturing the textural properties, are combined with the color feature while doing the CBIR. The retrieval performance on a large image database shows that the proposed technique provides a better accuracy compared to other multi-resolution based approaches.
- 1.Bimbo, A.D.: Visual Information Retrieval. Morgan Kaufman Publishers, Inc., San Francisco (2001)Google Scholar
- 5.Jhanwar, N., Chaudhuri, S., Seetharaman, G., Zavidovique, B.: Content based image retrieval using motif coocurence matrix. Image and Vision Computing 22, 1211–1220 (2004)Google Scholar
- 7.Kokare, M., Chatterji, B.N., Biswas, P.K.: Rotated wavelet based texture features for content based image retrieval. In: Fifth International Conference on Advances in Pattern Recognition, pp. 243–247 (2003)Google Scholar
- 8.Smith, J., Chang, S.F.: Visual seek: A fully automated conent based query system. In: Proc. ACM Multimedia, pp. 87–98. ACM Press, New York (1996)Google Scholar
- 9.Simoncelli, E.P., Adelson, E.H.: Non-seperable extensions of quadrature mirror filters to multiple dimensions. Proc. of IEEE: Special issue on Multidimensional Signal Processing 78, 652–664 (1990)Google Scholar
- 10.Do, M.N., Vitterli, M.: The contourlet transform:an efficient directional multiresolution image representation. IEEE Transactions on Image Processing (2004) (to appear)Google Scholar