Reconstructing Scanned Documents for Full-Text Indexing to Empower Digital Library Services

  • Melania Nitu
  • Mihai DascaluEmail author
  • Maria-Iuliana Dascalu
  • Teodor-Mihai Cotet
  • Silvia Tomescu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11984)


The digital era raises new challenges for traditional library services in which information has to be delivered and supported by technology-enhanced systems. The increasing need for rapid access to information requires librarians to re-evaluate the way they develop, manage and deliver resources, as well as services. However, most information extraction systems are not designed to work with PDF files generated after Optical Character Recognition, and several problems are encountered while trying to properly restructure the recognized text, for example: disruption of paragraphs, improper page breaks, or loss of content structure. This paper introduces a pre-processing pipeline designed to support university libraries to adequately index old document collections. The extracted text is indexed into Elasticsearch which facilitates the search for relevant documents, based on keywords. The information extraction system is designed to assist librarians in the digitization process by enabling a systematic review of documents, which leads to more accurate representations of the indexed files.


Preprocessing pipeline Text extraction Text indexing Unstructured documents 



This work was supported by a grant of the Romanian Ministry of Research and Innovation, CCCDI - UEFISCDI, project number PN-III-P1-1.2-PCCDI-2017-0689/“Lib2Life - Revitalizarea bibliotecilor si a patrimoniului cultural prin tehnologii avansate”/“Revitalizing Libraries and Cultural Heritage through Advanced Technologies”, within PNCDI III.


  1. 1.
    Biblioteca Centrala Universitara Carol I. Accessed 16 Aug 2019
  2. 2.
    Cervone, H.F.: Emerging technology, innovation, and the digital library. OCLC Syst. Serv. Int. Digit. Libr. Perspect. 26(4), 239–242 (2010)CrossRefGoogle Scholar
  3. 3.
    Schouten, K., Frasincar, F., Dekker, R., Riezebos, M.: Heracles: a framework for developing and evaluating text mining algorithms. Expert Syst. Appl. 127, 68–84 (2019)CrossRefGoogle Scholar
  4. 4.
    Korzen, C.: Icecite (2017). Accessed 16 Aug 2019
  5. 5.
    Santos, A., Matos, S., Campos, D., Oliveira, J.L.: A curation pipeline and web-services for PDF documents. In: CEUR Workshop Proceedings, vol. 1650. ISSN 1613-0073
  6. 6.
    Maciocci, G.: ScienceBeam - using computer vision to extract PDF data. Accessed 16 Aug 2019
  7. 7.
    Hassan, T.: Baumgartner, R.: Intelligent text extraction from PDF documents, pp. 2–6 (2005).
  8. 8.
    Sasirekha, D., Chandra, E.: Text extraction from PDF document. In: IJCA Proceedings on Amrita International Conference of Women in Computing, AICWIC, no. 3, pp. 17–19 (2013)Google Scholar
  9. 9.
    Ramakrishnan, C., Patnia, A., Hovy, E., Burns, G.: Layout-aware text extraction from full-text PDF of scientific articles. Source Code Biol. Med. 7(1), 7 (2012)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Melania Nitu
    • 1
  • Mihai Dascalu
    • 1
    Email author
  • Maria-Iuliana Dascalu
    • 2
  • Teodor-Mihai Cotet
    • 1
  • Silvia Tomescu
    • 3
  1. 1.Computer Science DepartmentUniversity Politehnica of BucharestBucharestRomania
  2. 2.Department of Engineering in Foreign LanguagesUniversity Politehnica of BucharestBucharestRomania
  3. 3.Central University Library of BucharestBucharestRomania

Personalised recommendations