Statistics of natural image categories

Antonio Torralba, Aude Oliva
2003 Network  
In this paper we study the statistical properties of natural images belonging to different categories and their relevance for scene and object categorization tasks. We discuss how second-order statistics are correlated with image categories, scene scale and objects. We propose how scene categorization could be computed in a feedforward manner in order to provide top-down and contextual information very early in the visual processing chain. Results show how visual categorization based directly
more » ... low-level features, without grouping or segmentation stages, can benefit object localization and identification. We show how simple image statistics can be used to predict the presence and absence of objects in the scene before exploring the image.
doi:10.1088/0954-898x/14/3/302 pmid:12938764 fatcat:6shsdbybgzchdev4aqsvndduge