Combining Neural Networks and Clustering Techniques for Object Recognition in Indoor Video Sequences

  • Francesc Serratosa
  • Nicolás Amézquita Gómez
  • René Alquézar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4225)


This paper presents the results obtained in a real experiment for object recognition in a sequence of images captured by a mobile robot in an indoor environment. Objects are simply represented as an unstructured set of spots (image regions) for each frame, which are obtained from the result of an image segmentation algorithm applied on the whole sequence. In a previous work, neural networks were used to classify the spots independently as belonging to one of the objects of interest or the background from different spot features (color, size and invariant moments). In this work, clustering techniques are applied afterwards taking into account both the neural net outputs (class probabilities) and geometrical data (spot mass centers). In this way, context information is exploited to improve the classification performance. The experimental results of this combined approach are quite promising and better than the ones obtained using only the neural nets.


Clustering Spot Class probabilities Neural Nets 


  1. 1.
    Sanfeliu, A., Serratosa, F., Alquézar, R.: Second-order random graphs for modeling sets of attributed graphs and their application to object learning and recognition. Int. Journal of Pattern Recognition and Artificial Intelligence 18(3), 375–396 (2004)CrossRefGoogle Scholar
  2. 2.
    Amezquita Gómez, N., Alquézar, R.: Object recognition in indoor video sequences by classifying image segmentation regions using neural networks. In: Sanfeliu, A., Cortés, M.L. (eds.) CIARP 2005. LNCS, vol. 3773, pp. 93–102. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  3. 3.
    Singh, S., Markou, M., Haddon, J.: Detection of new image objects in video sequences using neural networks. In: Nasrabadi, N.M., Katsaggelos, A.K. (eds.) Proc. SPIE. Applications of Artificial Neural Networks in Image Processing V, vol. 3962, pp. 204–213 (2000)Google Scholar
  4. 4.
    Fay, R., Kaufmann, U., Schwenker, F., Palm, G.: Learning object recognition in a neurobotic system. In: Groß, H.-M., Debes, K., Böhme, H.-J. (eds.) 3rd Workshop on SelfOrganization of AdaptiVE Behavior (SOAVE 2004). Fortschritt -Berichte VDI, Reihe 10 Informatik / Kommunikation, vol. 743, pp. 198–209. VDI Verlag, Düsseldorf (2004)Google Scholar
  5. 5.
    Wang, W., Zhang, A., Song, Y.: Identification of objects from image regions. In: IEEE Int. Conf. on Multimedia and Expo (ICME 2003), Baltimore, July 6-9 (2003)Google Scholar
  6. 6.
    Felzenszwalb, P., Huttenlocher, D.: Efficiently computing a good segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 98–104 (1998)Google Scholar
  7. 7.
    Hu, M.-K.: Visual pattern recognition by moment invariants. IRE Trans. on Information Theory 8(2), 179–187 (1962)CrossRefGoogle Scholar
  8. 8.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Francesc Serratosa
    • 1
  • Nicolás Amézquita Gómez
    • 1
  • René Alquézar
    • 2
  1. 1.Departament d’Enginyeria Informàtica i MatemàtiquesUniversitat Rovira i VirgiliTarragonaSpain
  2. 2.Dept. Llenguatges i Sistemes InformàticsUniversitat Politècnica de CatalunyaBarcelonaSpain

Personalised recommendations