Ontology-Assisted Object Detection: Towards the Automatic Learning with Internet

  • Francesco Setti
  • Dong-Seon Cheng
  • Sami Abduljalil Abdulhak
  • Roberta Ferrario
  • Marco Cristani
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8157)

Abstract

Automatic detection approaches depend essentially on the use of classifiers, that in turn are based on the learning of a given training set. The choice of the training data is crucial: even if this aspect is often neglected, the visual information contained in the training samples can make the difference in a detection/classification scenario. A good training set has to be sufficiently informative to capture the nature of the object under analysis, but at the same time has to be generic enough to avoid overfitting and to cope with new instances of the object of interest. In this paper we follow those approaches that pursue automatic learning from Internet data. We try to show how such training set can be made more appropriate by leveraging on semantic technologies, like lexical resources and ontologies, in the task of retrieving images from the Web through the use of a search engine. Experiments on several object classes of the CalTech101 dataset promote our idea, showing an average increment on the detection accuracy of about 8%.

Keywords

object detection one-class SVM machine learning ontology semantic search 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bunescu, R., Mooney, R.: Multiple instance learning for sparse positive bags. In: ICML 2007, pp. 105–112. ACM, New York (2007)Google Scholar
  2. 2.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106(1), 59–70 (2007)CrossRefGoogle Scholar
  3. 3.
    Fellbaum, C.: Wordnet and wordnets. In: Brown, K. (ed.) Encyclopedia of Language and Linguistics, pp. 665–670. Elsevier, Oxford (2005)Google Scholar
  4. 4.
    Helmer, S., Meger, D., Viswanathan, P., McCann, S., Dockrey, M., Fazli, P., Southey, T., Muja, M., Joya, M., Little, J., Lowe, D., Mackworth, A.: Semantic robot vision challenge: Current state and future directions. CoRR (2009)Google Scholar
  5. 5.
    Lopes, L.S., Chauhan, A.: How many words can my robot learn? an approach and experiments with one-class learning. Interaction Studies 8, 53–81 (2007)CrossRefGoogle Scholar
  6. 6.
    Masolo, C., Borgo, S., Gangemi, A., Guarino, N., Oltramari, A.: Wonderweb deliverable d18. Tech. rep., CNR (2003)Google Scholar
  7. 7.
    Meger, D., Muja, M., Helmer, S., Gupta, A., Gamroth, C., Hoffman, T., Baumann, M., Southey, T., Fazli, P., Wohlkinger, W., Viswanathan, P., Little, J., Lowe, D., Orwell, J.: Curious george: An integrated visual search platform. In: CRV, pp. 107–114 (2010)Google Scholar
  8. 8.
    Popescu, A., Millet, C., Moëllic, P.A.: Ontology driven content based image retrieval. In: CIVR, pp. 387–394 (2007)Google Scholar
  9. 9.
    Prévot, L., Borgo, S., Oltramari, A.: Ontology and the lexicon: a multi-disciplinary perspective (introduction). Studies in Natural Language Processing, pp. 185–200. Cambridge University Press (April 2010)Google Scholar
  10. 10.
    Roy, D., Pentland, A.: Learning words from sights and sounds: A computational model (1999), http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.34.9295
  11. 11.
    Schroff, F., Criminisi, A., Zisserman, A.: Harvesting image databases from the web. In: ICCV (2007)Google Scholar
  12. 12.
    Setz, A.T., Snoek, C.G.M.: Can social tagged images aid concept-based video search? In: ICME (2009)Google Scholar
  13. 13.
    Steels, L., Kaplan, F.: Aibo’s first words: The social learning of language and meaning. Evol. of Communication 4(1), 3–32 (2001)CrossRefGoogle Scholar
  14. 14.
    Ulges, A., Schulze, C., Koch, M., Breuel, T.: Learning automatic concept detectors from online video. Comput. Vis. Image Underst. 114(4), 429–438 (2010)CrossRefGoogle Scholar
  15. 15.
    Vijayanarasimhan, S., Grauman, K.: Keywords to visual categories: Multiple-instance learning for weakly supervised object categorization. In: CVPR (2008)Google Scholar
  16. 16.
    Yeh, T., Darrell, T.: Dynamic visual category learning. In: CVPR (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Francesco Setti
    • 1
  • Dong-Seon Cheng
    • 2
  • Sami Abduljalil Abdulhak
    • 3
  • Roberta Ferrario
    • 1
  • Marco Cristani
    • 3
    • 4
  1. 1.ISTC–CNRTrentoItaly
  2. 2.Hankuk University of Foreign StudiesYonginCorea
  3. 3.Università degli Studi di VeronaVeronaItaly
  4. 4.Istituto Italiano di Tecnologia (IIT)GenovaItaly

Personalised recommendations