%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi@80/2008/07.18.15.15
%2 sid.inpe.br/sibgrapi@80/2008/07.18.15.15.42
%@doi 10.1109/SIBGRAPI.2008.9
%T Automatic produce classification from images using color, texture and appearance cues
%D 2008
%A Rocha, Anderson,
%A Hauagge, Daniel C.,
%A Wainer, Jacques,
%A Goldenstein, Siome,
%@affiliation Institute of Computing, University of Campinas (Unicamp)
%@affiliation Institute of Computing, University of Campinas (Unicamp)
%@affiliation Institute of Computing, University of Campinas (Unicamp)
%@affiliation Institute of Computing, University of Campinas (Unicamp)
%E Jung, Cláudio Rosito,
%E Walter, Marcelo,
%B Brazilian Symposium on Computer Graphics and Image Processing, 21 (SIBGRAPI)
%C Campo Grande, MS, Brazil
%8 12-15 Oct. 2008
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%K Produce classification, multi-class categorization, produce data set.
%X We propose a system to solve a multi-class produce categorization problem. For that, we use statistical color, texture, and structural appearance descriptors (bag-of-features). As the best combination setup is not known for our problem, we combine several individual features from the state-of-the-art in many different ways to assess how they interact to improve the overall accuracy of the system. We validate the system using an image data set collected on our local fruits and vegetables distribution center.
%@language en
%3 rocha-AutomaticProduceClassification.pdf