Semantic-Based Search Engine System for Graph Images in Academic Literature

  • Sarunya KanjanawattanaEmail author
  • Masaomi Kimura
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 532)


It is well known that information retrieval is an essential aspect of search engine systems because there is a very large amount of data published on the internet that cannot be manually searched. However, search engine systems should not only present relevant results but also obtain new knowledge from the user’s searches. For example, new knowledge in academic research areas may be present in images that include graphs. In this study, we utilize methods to extract graphical and textual information from graph images and store this new knowledge in an ontology. We also propose a search engine system that is applicable to an ontology that contains this extractable information, which is extracted from images with graphs. The developed ontology is useful because users can acquire considerable amount of knowledge that is discovered from the semantic relations in the ontology. To evaluate the search engine system, we conducted four simulations to address four main issues. The results indicate that the proposed system provides accurate and relevant results; moreover, as indicated by the high F-measure values, the performance of the system is highly acceptable. However, we also found some limitations, which will be mitigated in a future study.


  1. 1.
    Y. Tsuruoka, J. Tsujii, S. Ananiadou, Facta: a text search engine for finding associated biomedical concepts. Bioinformatics 24(21), 2559–2560 (2008)CrossRefGoogle Scholar
  2. 2.
    M. Batko, F. Falchi, C. Lucchese, D. Novak, R. Perego, F. Rabitti, J. Sedmidubsky, P. Zezula, Building a web-scale image similarity search system. Multimed. Tools Appl. 47(3), 599–629 (2010)CrossRefGoogle Scholar
  3. 3.
    J.-q. Ma, Content-based image retrieval with HSV color space and texture features, in Proceedings of the 2009 International Conference on Web Information Systems and Mining (IEEE Computer Society, Piscataway, 2009), pp. 61–63CrossRefGoogle Scholar
  4. 4.
    S. Kanjanawattana, M. Kimura, Extraction and identification of bar graph components by automatic epsilon estimation. Int. J. Comput. Theory Eng. 9(4), 256–261 (2017)CrossRefGoogle Scholar
  5. 5.
    S. Kanjanawattana, M. Kimura, Extraction of graph information based on image contents and the use of ontology, in International Conferences ITS, ICEduTech and STE 2016, pp. 19–26 (2016)Google Scholar
  6. 6.
    S. Kanjanawattana, M. Kimura, A proposal for a method of graph ontology by automatically extracting relationships between captions and x- and y-axis titles, in Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, pp. 231–238 (2015)Google Scholar
  7. 7.
    J. Euzenat, P. Shvaiko et al., Ontology Matching, vol. 18 (Springer, Berlin, 2007)zbMATHGoogle Scholar
  8. 8.
    G. Li, S. Ji, C. Li, J. Feng, Efficient fuzzy full-text type-ahead search. VLDB J. Int. J. Very Large Data Bases 20(4), 617–640 (2011)CrossRefGoogle Scholar
  9. 9.
    T. Jayalakshmi, C. Chethana, A semantic search engine for indexing and retrieval of relevant text documents. Int. J. Adv. Res. Comput. Sci. 4(5), 1–5 (2016)Google Scholar
  10. 10.
    A. Both, A.-C.N. Ngomo, R. Usbeck, D. Lukovnikov, C. Lemke, M. Speicher, A service-oriented search framework for full text, geospatial and semantic search, in Proceedings of the 10th International Conference on Semantic Systems, pp. 65–72 (ACM, New York, 2014)Google Scholar
  11. 11.
    S. Kanjanawattana, M. Kimura, Novel ontologies-based optical character recognition-error correction cooperating with graph component extraction. BRAIN. Broad Res. Artif. Intell. Neurosci. 7(4), 69–83 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Shibaura Institute of TechnologyTokyoJapan

Personalised recommendations