Application of semantic web technologies for automatic multimedia annotation
Ruben Verborgh, Davy Van Deursen, Erik Mannens, Chris Poppe, Rik Van de Walle · Ghent University Academic Bibliography (Ghent University) · 2010
The generation of metadata, facilitating the retrieval of multimedia items, requires a large amount of manual work.Several processing algorithms that automate parts of this task exist, but they lack a global vision on the object under annotation.In this paper, we investigate how we can apply Semantic Web knowledge to integrate and enhance current processing algorithms in order to answer more advanced metadata queries.We propose a generic problem-solving platform that uses Web services and various knowledge sources to find solutions to complex requests.The platform employs a reasonerbased composition algorithm, generating an execution plan that combines several algorithms as services.It then supervises the execution of this plan, intervening in case of errors or unexpected behavior.We illustrate our approach by a use case in which we annotate the names of people depicted in a photograph.