Issue No.03 - July-September (1999 vol.6)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/93.790610
A compositional approach increases the level of representation that can be automatically extracted and used in a visual information retrieval system. Visual information at the perceptual level is aggregated according to a set of rules. These rules reflect the specific context and transform perceptual words into phrases capturing pictorial content at a higher, and closer to the human, semantic level.
Carlo Colombo, Alberto Del Bimbo, Pietro Pala, "Semantics in Visual Information Retrieval", IEEE MultiMedia, vol.6, no. 3, pp. 38-53, July-September 1999, doi:10.1109/93.790610