Semi – automated tool for characterizing news video files, using metadata schemas

  • Stefanos Asonitis
  • Dimitris Boundas
  • Georgios Bokos
  • Marios Poulos

The size increment of online TV's video repositories, rises the necessity of an effective automated video content-based retrieval service. Our project will give a partial answer to that problem by developing a semi-automated tool for characterizing broadcast news video files. Our tool will be constituted of two sections. In the first section, the repositories' video files will be separated from their audio content. Then the audio content will be characterized by a classification system in two predefined categories,: news and sports. In the second section the audio files will be described using proper description languages such as NewsML and SportsML, thus characterizing the initial video file they came from. The effectiveness of our semi-automated tool will be tested in a local repository of news video files, created by a customizable, focuses on video files, data mining web crawler.


Audio Signal Video File Sport Event News Event Sport Video 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Adami, N., Bugatti, A., Leonardi, R., Migliorati, P.: Low Level Processing of Audio and Video Information for Extracting the Semantics of Content. IEEE Fourth Workshop on Multimedia Signal Processing (2001)Google Scholar
  2. 2.
    Allday, T.: “ NewsML: enabling a standards-led revolution in news publishing?”. Reuters Media Group, EBU Technical Review (2001).Google Scholar
  3. 3.
    Barrat, K., Miller, R.: SPHINX: A Framework for Creating Personal, Site-Specific Web Crawlers. Printed in Computer Network and ISDN Systems v.30. Brisbane, Australia, pp. 119–130 (1998)Google Scholar
  4. 4.
    Brown, M., Foote, J., Jones, K., Young, S.: Automatic Content-Based Retrieval of Broadcast News: Proceedings of the third ACM international conference on Multimedia, pp. 35-43 (1995)Google Scholar
  5. 5.
    Fogarty, T. C.: Classifier systems for control. IEEE Colloquim on Genetic Algorithms for Control Systems Engineering (1993)Google Scholar
  6. 6.
    Greenberg, J., Spugrin, K. 'Crystal, A. : Functionalities for automatic metadata generation applications: a survey of metadata experts' opinions, International Journal of Metadata, Semantics and Ontologies vol. 1 no. 1 pp. 3-20 (2006)CrossRefGoogle Scholar
  7. 7.
    Kokaram, A., Rea, N., Dahyot, R., Tekalp, M., Bouthemy, P., Gros, P., Sezan, I. : Browsing sports video: trends in sports-related indexing and retrieval work. IEEE Signal Processing Magazine, Volume 23, Issue 2, pp. 47 — 58 (2006)Google Scholar
  8. 8.
    Michel, P., Kaliouby, R.: Real time facial expresion recognition in video using support vector machines. In Proceedings of ICMI ' 03.Google Scholar
  9. 9.
    Nitanda, N., Haseyama, M., Kitajima, H.: Accurate Audio-Segment Classification Using Feature Extraction Matrix. IEEE International Conference on Acoustics, Speech, and Signal Processing (2005)Google Scholar
  10. 10.
    The NewsML,
  11. 11.
    The SportsML,
  12. 12.
    Tsekeridou, S., MPEG-7 MDS based application specific metadata model for personalized multi-service access in a DTV broadcast environment.Google Scholar
  13. 13.
    Wales, C., Kim, S., Leuenberger, D., Watts, W., O WeinrothI, O.: IPTV — The Revolution is Here. (2005.)Google Scholar
  14. 14.
    Welz, M., Hutchison, A. : Modulating Access Control at the Application for Closely Coupled Intrusion Detection, 1st Computer Science Mini Conference, Cape Town, South Africa (2002)Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.Dept. Of Archives and Library SciencesIonian UniversityPalea AnaktoraGreece

Personalised recommendations