Review of the State of the Art in Semantic Scene Classification

We would also like to thank Amit Singhal, Bob Gray, Zhao-hui Sun, and Navid Serrano, all of Eastman Kodak Company, for their support and advice throughout the course of this research. Boutell's and Brown's contribution to this research was supported in part by a generous grant from Eastman Kodak Company under its external technology program. Some of the preliminary results were based on work performed at Kodak Research Labs. Their work was supported furthermore by the NSF under grant number EIA-0080124 and by the Department of Education (GAANN) grant number P200A000306. Any opinion, findings, and conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of Eastman Kodak Company or these agencies.Semantic scene classification, categorizing images into one of a set of physical (e.g., indoor/outdoor, orientation) or semantic categories (e.g., beach or party), is a relatively new field. Most of the existing techniques used primarily low-level features to classify scenes and achieved some success on constrained problems. We report on the state of the art, presenting summaries of major scene classification systems and identifying the features and inference engines they use