Improving Literature Preselection by Searching for Images

  • Brigitte Mathiak
  • Andreas Kupfer
  • Richard Münch
  • Claudia Täubner
  • Silke Eckstein
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3886)


In this paper we present a picture search engine for life science literature and show how it can be used to improve literature preselection. This preselection is needed as a way to compensate for the vast amounts of literature that are available. While searching for DNA binding sites for example, we wanted to add the results of specific experiments (DNAse I footprint and EMSA) to our database. The preselection via abstract search was very unspecific (150 000 hits), but by looking for paper with images concerning the experiments, we could improve precision immensely. They are displayed like hits in a search engine, allowing easy and quick quality assessment without having to read through the whole paper. The images are found by their annotation in the paper: the figure caption. To identify that, we analyse the layout of the paper: the position of the image and the surrounding text.


Search Engine Font Size Text Block Virtual Document Layout Information 
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.
  2. 2.
    Münch, R., Hiller, K., Barg, H., Heldt, H., Linz, S., Wingender, E., Jahn, D.: Prodoric: prokaryotic database of gene regulation. Nucleic Acids Research 31(1), 266–269 (2003)CrossRefGoogle Scholar
  3. 3.
    Faulstich, L.C., Stadler, P.F., Thurner, C., Witwer, C.: litsift: Automated text categorization in bibliographic search. In: Data Mining and Text Mining for Bioinformatics, Workshop at the ECML / PKDD 2003 (2003)Google Scholar
  4. 4.
    Yeh, A., Hirschman, L., Morgan, A.: Evaluation of text data mining for database curation: lessons learned from the kdd challenge cup. Bioinformatics 19(1) (2003)Google Scholar
  5. 5.
    Shah, P., Perez-Iratxeta, C., Bork, P., Andrade, M.: Information extraction from full text scientific articles: Where are the keywords? BMC Bioinformatics (2003)Google Scholar
  6. 6.
    Adobe Network Solutions: PDF Reference Fourth Edition (2004),
  7. 7.
  8. 8.
    Kovacevic, M., Diligenti, M., Gori, M., Milutinovic, V.: Visual Adjacency Multigraphs - a Novel Approach to Web Page Classification. In: Proceedings of SAWM 2004 workshop, ECML 2004 (2004)Google Scholar
  9. 9.
    Litchfield, B.: PDFBox (2004), or
  10. 10.
    The Apache Software Foundation: Digester (2005),
  11. 11.
    Hatcher, E., Gospodnetic, O.: Lucene in Action. Manning Publications (2004)Google Scholar
  12. 12.
    The Apache Software Foundation: Tomcat (2005),
  13. 13.
    Coward, D., Yoshida, Y.: Java Servlet Specification (2003),
  14. 14.
    Deutsch, L.: Deflate compressed data format specification. Request for Comments No 1951, Network Working Group (1996)Google Scholar
  15. 15.
    International Organization for Standardization: ISO/IEC 10918-1:1994: Information technology — Digital compression and coding of continuous-tone still images: Requirements and guidelines. International Organization for Standardization, Geneva, Switzerland (1994)Google Scholar
  16. 16.
    Galperin, M.Y.: The Molecular Biology Database Collection: 2005 update. Nucleic Acids Research 33(Database-Issue), 5–24 (2005)Google Scholar
  17. 17.
    Schmeier, S., Hakenberg, J., Kowald, A., Klipp, E., Leser, U.: Text mining for systems biology using statistical learning methods. In: 3. Workshop des Arbeitskreises Knowledge Discovery (2003)Google Scholar
  18. 18.
    Wang, Y., Phillips, I.T., Haralick, R.M.: Table detection via probability optimization. In: Lopresti, D.P., Hu, J., Kashi, R.S. (eds.) DAS 2002. LNCS, vol. 2423, pp. 272–283. Springer, Heidelberg (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Brigitte Mathiak
    • 1
  • Andreas Kupfer
    • 1
  • Richard Münch
    • 2
  • Claudia Täubner
    • 1
  • Silke Eckstein
    • 1
  1. 1.Institut für InformationssystemeTU BraunschweigGermany
  2. 2.Institut für MikrobiologieTU BraunschweigGermany

Personalised recommendations