Most of the data stored in libraries are in digital form will contain either pictures or video, which is tough to search or browse. Methods which are automatic for searching picture collections made large use of color histograms, because they are very strong to wide changes in viewpoint, and can be calculated trivially. However, color histograms unable to present spatial data, and therefore tend to give lesser results. By using combination of color information with spatial layout we have developed several methods, while retrieving the advantages of histograms. A method computes a given color as a function of the distance between two pixels, which we call a color correlogram. We propose a color-based image descriptor that can be used for image indexing based on high-level semantic concepts. The descriptor is based on Kobayashi’s Color Image Scale, which is a system that includes 130 basic colors combined in 1180 three-color combinations. The words are represented in a two dimensional semantic space into groups based on perceived similarity. The modified approach for statistical analysis of pictures involves transformations of ordinary RGB histograms. Then a semantic image descriptor is derived, containing semantic data about both color combinations and single colors in the image.
展开▼
