An Efficient CBIR Scheme Using Combined Features
In this paper, we propose a practical image retrieval scheme based on the issue of texture, color space and
relevance feedback features extractions. The algorithm for an effective image retrieval scheme to retrieve images is
presented. We propose a scheme using color and texture features and address the unique algorithm to extract the color pixel
features by the RGB color sequence coding, the texture features of Homogeneous Texture Descriptor (HTD) and relevance
feedback. The proposed scheme transfers each image to a quantized color code using the regulations of the properties in
compliance with RGB color sequence coding model and then employing the quantized color code, the texture feature of
Homogeneous Texture Descriptor (HTD) to compare the images of database along with relevance feedback feature.
Experimental of the proposed scheme performed on SIMPLI city image database to demonstrate more efficient and effective
than the conventional schemes.
Keywords- Homogeneous Texture Descriptor, RGB color sequence coding, Relevance feedback, Gabor filter