Information Extraction from Multimedia Documents for e-Government Applications
Despite the exponential growth of information systems for supporting public administration requirements, we are still far from a complete automatic e-government system. In particular, there exists the need of automatic or semi-automatic procedures for the whole flow of digital documents management, in particular regarding: (1) automatic information extraction from digital documents; (2) semantic interpretation (3) storing; (4) long term preservation and (5) retrieval of the extracted information. In addition, in the last few years the textual information has been enriched with multimedia data, having heterogeneous formats and semantics. In this framework, it’s the author’s opinion that an effective E-Government information system should provide tools and techniques for multimedia information, in order to manage both the multimedia content of a bureaucratic document and the presentation constraints that are usually associated to such document management systems. In this paper, we will describe a novel system that exploits both textual and image processing techniques, in order to automatically infer knowledge from multimedia data, thus simplifying the indexing and retrieval tasks. A prototypal version of the system has been developed and some preliminary experimental results have been carried out, demonstrating the efficacy in real application contexts.
KeywordsInformation Extraction Range Query Multimedia Data Multimedia Document Information Path
Unable to display preview. Download preview PDF.
- 1.Deliberation of 13 dicembre 2001, n. 42, published on Gazzetta Ufficiale della Repubblica Italiana n. 296 of 21 dicembre 2001.Google Scholar
- 3.D.A. Adjeroh, and K.C. Nwosu (1997), “Multimedia Database Management – Requirements and issues. iEEE Transaction Multimedia 4:24–33.Google Scholar
- 6.O. Udrea, V.S. Subrahmanian, and Z. Majkic, (2006) “Probabilistic RDF”, Proceedings of the 2006 IEEE International Conference on Information Reuse and Integration, IRI, pp. 172–177.Google Scholar
- 7.M.S. Lew, N. Sebe, D. Djeraba, and J. Rain, (2006) “Content-based multimedia information retrieval: State of the art and challenges”, ACM Transactions on Multimedia Computing, Communications and Applications, 2(1):1–19.Google Scholar
- 8.L. Reeve and H. Han, (2005) “Survey of semantic annotation platforms”, in Proceedings of the 2005 ACM symposium on Applied computing, pp. 1634–1638.Google Scholar