CONTENT BASED VISUAL INFORMATION RETRIEVAL FOR MANAGEMENT INFORMATION SYSTEMS
Oleg Starostenko, J. Alfredo Sánchez, Roberto Rosas, Alberto Chávez-Aragón · 2007
This paper presents the results of our research dev oted to development of efficient methods for retrieval and indexing of documents with multim edia information that can help a business work smarter and gain an important advantage in whatever that business does. Particularly, a novel hybrid method for visual information retrieva l (VIR) is proposed. It combines shape analysis of objects in image with their automatic i ndexing by textual descriptions applying semantic Web approaches. A decision about similarit y between a retrieved image and user queries is taken by computing the shape star field or two-segment turning functions combining them with matching of ontological annotations of objects in image providing in this way the machine-understandable semantics. For analysis of this method the image retrieval IRONS (Image Retrieval by Ontological Description of Shapes) system has been implemented and evaluated in some specific image domains.