We introduce an innovative image retrieval algorithm, the Dynamic Spatial Chromatic Histogram, that makes it possible to take into account spatial information in a flexible way without drastically increasing the computation cost. The results of experimental trials on a database of about 3000 images are here reported and compared with Spatial Chromatic Histogram matching and more standard techniques based on human perceptual judgments to demonstrate the effectiveness of the algorithm proposed.
G. Ciocca, R. Schettini, L. Cinque, "Image Indexing and Retrieval Using Spatial Chromatic Histograms and Signatures" in Proc. IS&T CGIV 2002 First European Conf. on Colour in Graphics, Imaging, and Vision, 2002, pp 255 - 258, https://doi.org/10.2352/CGIV.2002.1.1.art00055