Color-Shape Based Image Retrieval
Sun Jim · 2004
In this study, a new image retrieval algorithm based on region color and spatial information is presented. Concerning the color information, the perceptually uniform HSV color space has been employed. The method presents a new way to localize the characteristics of the queries by partitioning the image into m × n equal-sized sub-images (or blocks )and applying different features to each block in the similarity measuring phase. A hue that has enough number of pixels in a block is extracted to represent its content and the whole image content is represented by the extracted hues of the blocks,after that,hue histogram is used as the description of the image color feature. In order to extract the shape feature of the image,two notions .flatness and roughness of the sub-image are proposed in this paper. Using these two properties the blocks of the image are quantified into different types. The histogram of the types is used to represent the shape feature of the entire image. Experiments show that this algorithm is more effective in the image retrieval than the other algorithms discussed in the paper.