基于颜色和形状的图像检索

Color-Shape Based Image Retrieval

在分析了基于图像颜色信息和空间信息进行图像检索的基础上,提出了一种新的基于图像颜色和形状的图像检索算法。该算法采用HSI颜色空间,整幅图像首先被划分为具有固定尺寸的分块,对其中的每一分块,提取该分块的主色调作为该分块的颜色特征,对整幅图像采用主色调直方图作为其颜色特征;在对图像形状特征的提取上,针对图像Ⅰ分量的每一分块,提出了分块平坦度和凹凸度的概念,并利用分块的这两个属性,将图像的分块划分为不同类别,同时采用不同类别分块的直方图作为图像的形状特征。试验表明利用该算法提取的图像的颜色特征和形状特征在进行图像检索时效果显著。

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.