COLOR TEXTURED IMAGE RETRIEVAL BY COMBINING TEXTURE AND COLOR FEATURES

A new approach for color textured image retrieval based on the combination of color and texture features is proposed. The features are extracted in DCT domain. For texture featuring, Texture-Pattern is proposed to be constructed by using three groups of AC coefficients of each DCT block from the luminance component. And for color featuring, LumaColor-Pattern is constructed by using the DC coefficients from the luminance and chroma components. The histograms of dominant components of these two patterns are constructed and their combination is used for image retrieval. Experimental results on VisTex database have shown that the proposed method yields higher performance than referred approaches which are reported in recently published literature.