A integrated color-spatial image representation and the similar image retrieval

In this paper, we focus on similar image retrieval based on color-content. A two-phase matching strategy is adopted for achieving speed and accuracy of the proposed retrieval: the first phase of matching is intended to produce a candidate image list which are similar to the sample image using the global color histogram; the second phase of matching acts as a filter on the list obtained by the first phase, deleting dissimilar images using the spatial distribution of colors in the image. It is common knowledge that most of the images are dominated by a small number of colors, called dominant colors. We propose dominant color matrices for representing the spatial distribution of dominant colors in an image, which can serve as a basis for measuring the spatial similarity between images. In order to calculate the spatial similarity on dominant color matrices, we use two-dimensional DP matching technology extended from conventional DP matching. In addition, we have also applied the proposed approach to a range of color images, and obtained positive results.