Authors: Antonio M. Rinaldi
Addresses: DIETI – Dipartimento di Ingegneria Elettrica e delle Tecnologie, dell'Informazione 80125 Via Claudio, 21, Napoli, Italy; IKNOS-LAB – Intelligent and Knowledge Systems-LUPT, Universita di Napoli Federico II, 80134 Via Toledo, 402, Napoli, Italy
Abstract: The managing of large amounts of data in digital ecosystems and in big data environments requires the use of formal models and techniques to represent and organise information. In this paper, we describe a novel framework to manage multimedia ontologies using a knowledge engineering approach. The proposed methodology is based on multimedia ontologies organised following a formal model. Our ontologies use multimedia data and linguistic properties to bridge the gap between the target semantic classes and the available low-level multimedia descriptors. The multimedia features are automatically extracted using algorithms based on MPEG-7 standard. In our approach, multimedia ontologies are used to annotate and categorise images. The informative image content is annotated with semantic information extracted from our ontologies and the categories are dynamically built by means of a general knowledge base. The multimedia ontologies are exposed by means of web services and a peer-to-peer (P2P) architecture to allow their reuse and sharing. A complete use case example is presented and experimental results show the efficiency of our approach in the annotation and classification tasks using a combination of textual and visual components.
Keywords: multimedia ontologies; digital ecosystems; information sharing; peer-to-peer; P2P; OWL; ontology management; big data; knowledge engineering; image content; annotation; semantic information; web services; classification; textual components; visual components.
International Journal of Business Process Integration and Management, 2015 Vol.7 No.4, pp.274 - 288
Published online: 15 Dec 2015 *Full-text access for editors Access for subscribers Purchase this article Comment on this article