Object Detection and Feature Base Learning with Sparse Convolutional Neural Networks

  • Alexander R. T. Gepperth
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4087)


A new convolutional neural network model termed sparse convolutional neural network (SCNN) is presented and its usefulness for real-time object detection in gray-valued, monocular video sequences is demonstrated. SCNNs are trained on ”raw” gray values and are intended to perform feature selection as a part of regular neural network training. For this purpose, the learning rule is extended by an unsupervised component which performs a local nonlinear principal components analysis: in this way, meaningful and diverse properties can be computed from local image patches. The SCNN model can be used to train classifiers for different object classes which share a common first layer, i.e., a common preprocessing. This is of advantage since the information needs only to be calculated once for all classifiers. It is further demonstrated how SCNNs can be implemented by successive convolutions of the input image: scanning an image for objects at all possible locations is shown to be possible in real-time using this technique.


Hide Layer Mean Square Error Object Detection Learning Rule Object Class 
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.


  1. 1.
    Garcia, C., Delakis, M.: Convolutional face finder: A neural architecture for fast and robust face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(11), 1408–1423 (2004)CrossRefGoogle Scholar
  2. 2.
    Gepperth, A.: Visual object classification by sparse convolutional networks. In: Proceedings of the European Symposium on Artificial Neural Networks (ESANN) 2006, d-side publications (accepted, 2006)Google Scholar
  3. 3.
    Gepperth, A., Edelbrunner, J., Bücher, T.: Real-time detection of cars in video sequences. In: Proceedings of the IEEE Intelligent Vehicles Symposium (2005)Google Scholar
  4. 4.
    Hyvärinen, A.: Fast and robust fixed-point algorithms for independent component analysis. IEEE Transactions on Neural Networks 10, 626–634 (1999)CrossRefGoogle Scholar
  5. 5.
    Igel, C., Hüsken, M.: Empirical evaluation of the improved Rprop learning algorithm. Neurocomputing 50(C), 105–123 (2003)MATHCrossRefGoogle Scholar
  6. 6.
    Jähne, B.: Digital image processing. Springer, Heidelberg (1999)Google Scholar
  7. 7.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  8. 8.
    Reed, R.D., Marks II, R.J.: Neural Smithing. MIT Press, Cambridge (1999)Google Scholar
  9. 9.
    Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nature Neuroscience 2(11), 1019–1025 (1999)CrossRefGoogle Scholar
  10. 10.
    Roth, D.: The SNoW learning architecture. Technical Report UIUCDCS-R-99-2101, UIUC Computer Science Department (May 1999)Google Scholar
  11. 11.
    Szarvas, M., Yoshizawa, A., Yamamoto, M., Ogata, J.: Pedestrian detection using convolutional neural networks. In: Proceedings of the IEEE Symposium on Intelligent Vehicles, pp. 224–229 (2005)Google Scholar
  12. 12.
    Wersing, H., Körner, E.: Unsupervised learning of combination features for hierarchical recognition models. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, Springer, Heidelberg (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Alexander R. T. Gepperth
    • 1
  1. 1.Institute for Neural DynamicsBochumGermany

Personalised recommendations