%0 Conference Proceedings
%4 sid.inpe.br/banon/2002/11.05.10.29
%2 sid.inpe.br/banon/2002/11.05.10.29.55
%@doi 10.1109/SIBGRA.2000.883895
%T Target search by bottom-up and top-down fuzzy information
%D 2000
%A Neves, Evelina Maria de Almeida,
%A Borelli, Joćo Eduardo,
%A Gonzaga, Adilson,
%E Carvalho, Paulo Cezar Pinto,
%E Walter, Marcelo,
%B Brazilian Symposium on Computer Graphics and Image Processing, 13 (SIBGRAPI)
%C Gramado, RS, Brazil
%8 17-20 Oct. 2000
%I IEEE Computer Society
%J Los Alamitos
%P 60-66
%S Proceedings
%1 SBC - Brazilian Computer Society
%K visual perception, target search, bottom-up fuzzy information, top-down fuzzy information, feature extraction, visual field, human visual attention, fuzzy net, fuzzy subsystems, decision rules, visual perception, Gestalt laws, salience index, geometrical objects.
%X One of the basic tasks assigned to the attentional mechanism is to decide which location in the visual field we must pay attention first. An object containing a distinctive feature can attract attention in a bottom-up way. By comparing one object with the others present in the scene, bottom-up conspicuity features are used to guide attention to the most different object. Top-down hints are based on the previous knowledge about the objects or on which features are important to locate them and also have a large influence on the attended locations. Inspired by the mechanisms of human visual attention we developed a new methodology to integrate bottom-up and top-down information by using a fuzzy net containing three fuzzy subsystems. The first bottom-up subsystem allow us to combine features and infer with great flexibility some intuitive decision rules based on the visual perception principles such as the Gestalt laws. The second top-down subsystem combines different features according to the relevance of them in different tasks. Finally, the last subsystem integrates the information of the previous systems and gives a general salience index. The new methodology was tested in geometrical objects considering the features that attract attention to human beings.
%3 60-66.pdf
%O The conference was held in Gramado, RS, Brazil, from October 17 to 20.