作者: Ilaria Bartolini , Paolo Ciaccia , Marco Patella
关键词:
摘要: In this paper we describe PIBE, a new Personalizable Image Browsing Engine that allows an effective visual exploration of large image collections combining computer vision and database techniques. The principal features PIBE include the possibility modifying browsing structure by means graphical personalization actions provided interface, persistently storing such customizations for subsequent sections. hierarchical structure, called Tree, can be locally customized, thus avoiding global reorganizations, which are clearly unfeasible with collections. Indeed, each node Tree has associated cluster images specific dissimilarity function. We present basic principles engine, report some experimental results showing effectiveness efficiency functionalities provided.