Search

In this paper, we are interested in the problem of finding similar images in a large database. For this purpose we propose a new algorithm based on a combination of the 2-D histogram intersection in the HSV space and statistical moments. The proposed histogram is based on a 3x3 window and not only on the intensity of the pixel. This approach overcome the drawback of the conventional 1-D histogram which is ignoring the spatial distribution of pixels in the image, while the statistical moments are used to escape the effects of the discretisation of the color space which is intrinsic to the use of histograms. We compare the performance of our new algorithm to various methods of the state of the art and we show that it has several advantages. It is fast, consumes little memory and requires no learning. To validate our results, we apply this algorithm to search for similar images in different image databases., {"references":["Niblack, W., Barber, R., Equitz, W., Flickner, M., Glasman, E.,\nPetkovic, D., Yanker, P., Faloutsos, C., & Taubin, G. \"The QBIC\nProject: Querying Images by Content Using 37 Color, Texture, and\nShape\". SPIE Int. Symp. On Electronic Imaging: Science and\nTechnology Conf. 1908, Storage and Retrieval for Image and Video\ndatabases. (1993).","Carson, C., Thomas, M., Belongie, S., Hellerstein, J. M., & J. Malik.\n\"Blobworld: A System for Region-based Image Indexing and Retrieval\",\nProc. Third Int. Conf. on Visual Information Systems, June. (1999).","Clément, A., Vigouroux, B. \"Unsupervised segmentation of scenes\ncontaining vegetation (Forsythia) and soil by hierarchical analysis of bidimensional\nhistograms\". Patt. Recogn. Lett, Vol. 24, 1951–1957.\n(2003).","Masmoudi, Lh., Zennouhi, R., & EL Ansari, M. Participation with a\nchapter «Image Segmentation Based on Two Dimensional Histogram»\nin a book «image segmentation» published by InTech, (2011).","Cheng, H. D., Jiang, X. H., Sun, Y., Wang, J. \"Color image\nsegmentation: advances and prospects\". Pattern Recognition, Vol.34,\nNo.6, 2259-2281. (2001).","Zennouhi, R.., Masmoudi, L. H. \"A new 2D histogram scheme for color\nimage segmentation\". The Imaging Science Journal, Vol. 57, 260-265.\n(2009).","Sural, S., Qian, G., Pramanik, S. \"Segmentation and histogram\ngeneration using the HSV color space for image retrieval\", Proc. Int.\nConf. on Image processing: ICIP'02, Rochester, NY, USA, IEEE, Vol.\n2, pp. II589–II592. (2002).","Abutaleb, A. S. \"Automatic thresholding of gray-level pictures using\ntwo-dimensional entropy\". Journal of Computer Vision, Graphic and\nImage Process, Vol. 47, 22–32. (1989).","Zhang, Y. F., Zhang, Y. \"Another Method of Building 2D Entropy to\nRealize Automatic Segmentation\". Journal of Physics Conference\nSeries, Vol. 48, 303–307. (2006).\n[10] Swain M.J., Ballard D.H., \"Color indexing\". International Journal of\nComputer Vision, vol. 7, no. 1, pp. 11-22. (1991).\n[11] Stricker, M., Orengo, M. \"Similarity of Color Images\", In Proceedings\nof SPIE, Vol. 2420 (Storage and Retrieval of Image and Video\nDatabases III), SPIE Press, Feb. (1995).\n[12] Iqbal, Q., Aggarwal, J. K. (2002), \"Combining structure, color and\ntexture for image retrieval: a performance evaluation\". Proc. of\nInternational Conference on Pattern Recognition (ICPR), Quebec\n(Canada). (2002).\n[13] Penn state university's web page for modeling objects, concepts, and\naesthetics in images project. Online available at:\nhttp://wang.ist.psu.edu/docs/related/.\n[14] Coil (Columbia Object Image Library)dataset, Online available at:\nhttp://www1.cs.columbia.edu/CAVE/research/softlib/\n[15] The Fei-Fei dataset, Online available at:\nhttp://www.vision.caltech.edu/feifeili/Datasets.htm."]}