Color Image Retrieval Based on Mixture Approximation and Color Region Matching
The paper introduces the extension of the color image retrieval method based on the approximation of the perceptual parameters. The proposed solution enables effective search for similar images regardlessly of the applied compression scheme not only taking into account the color palette and the presence of regions of the homogenous color within the image, but also their spatial arrangement. The proposed method utilizes the Gaussian Mixture Modeling combined with the Bilateral Filtering approach along with color matching method based on dominant region color. The evaluated results show that satisfactory retrieval results can be obtained regardlessly to applied compression schemes, preserving the spatial arrangement of the color regions in evaluated results.
KeywordsGaussian Mixture Model Image Retrieval Query Image Color Histogram Retrieval Result
Unable to display preview. Download preview PDF.
- 3.Bilmes, J.: A Gentle tutorial on the EM algorithm and its application to parameter estimation for Gaussian Mixture and Hidden Markov Models. Technical Report, University of Berkeley, ICSI-TR-97-021 (1997)Google Scholar
- 6.Gray, R.M.: Gauss mixture vector quantization. In: Proceedings of IEEE ICASSP, vol. 3, pp. 1769–1772 (2005)Google Scholar
- 8.Jeong, S.: Distributional distances in color image retrieval with GMVQ-generated histograms. LNCS, vol. 3569, pp. 465–475. Springer, Heidelberg (2005)Google Scholar
- 11.Luszczkiewicz, M., Smolka, B.: Application of bilateral filtering and Gaussian Mixture modeling for the retrieval of paintings. In: Proceedings of the International Conference on image Processing (ICIP 2009), pp. 77–80 (2009)Google Scholar
- 13.Ohashi, T., Aghbari, Z., Makinouchi, A.: Hill-climbing algorithm for efficient color-based image segmentation. In: Proc. of IAESTED International Conference on Signal Processing, Pattern Recognition, and Applications (2003)Google Scholar
- 14.Plataniotis, K.N., Venetsanopoulos, A.N.: Color Image Processing and Application. Springer, Berlin (2000)Google Scholar