Advertisement

Fast Image Representation with GPU-Based Growing Neural Gas

  • José García-Rodríguez
  • Anastassia Angelopoulou
  • Vicente Morell
  • Sergio Orts
  • Alexandra Psarrou
  • Juan Manuel García-Chamizo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6692)

Abstract

This paper aims to address the ability of self-organizing neural network models to manage real-time applications. Specifically, we introduce a Graphics Processing Unit (GPU) implementation with Compute Unified Device Architecture (CUDA) of the Growing Neural Gas (GNG) network. The Growing Neural Gas network with its attributes of growth, flexibility, rapid adaptation, and excellent quality representation of the input space makes it a suitable model for real time applications. In contrast to existing algorithms the proposed GPU implementation allow the acceleration keeping good quality of representation. Comparative experiments using iterative, parallel and hybrid implementation are carried out to demonstrate the effectiveness of CUDA implementation in representing linear and non-linear input spaces under time restrictions.

Keywords

Growing Neural Gas topology preservation objects representation Graphics Processing Units Compute Unified Device Architecture parallelism 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ji, S., Park, W.: Image Segmentation of Color Image Based on Region Coherency. In: Proc. International Conference on Image Processing, pp. 80–83 (1998)Google Scholar
  2. 2.
    Lo, Y.S., Pei, S.C.: Color Image Segmentation Using Local Histogram and Self-organization of Kohonen Feature Map. In: Proc. International Conference on Image Processing, pp. 232–239 (1999)Google Scholar
  3. 3.
    Flórez, F., García, J.M., García, J., Hernández, A.: Representation of 2D Objects with a Topology Preserving Network. In: Proceedings of the 2nd International Workshop on Pattern Recognition in Information Systems (PRIS 2002), Alicante, pp. 267–276. ICEIS Press (2001)Google Scholar
  4. 4.
    Holdstein, Y., Fischer, A.: Three-dimensional Surface Reconstruction Using Meshing Growing Neural Gas (MGNG). Visual Computation 24, 295–302 (2008)CrossRefGoogle Scholar
  5. 5.
    Fritzke, B.: A Growing Neural Gas Network Learns Topologies. In: Tesauro, G., Touretzky, D.S., Leen, T.K. (eds.) Advances in Neural Information Processing Systems 7, pp. 625–632. MIT Press, Cambridge (1995)Google Scholar
  6. 6.
    Kohonen, T.: Self-Organising Maps. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  7. 7.
    Martinetz, T., Schulten, K.: Topology Representing Networks. Neural Networks 7(3), 507–522 (1994)CrossRefGoogle Scholar
  8. 8.
    NVIDIA Corporation, CUDA Programming Guide, version 3.2 (2010)Google Scholar
  9. 9.
    O’Rourke, J.: Computational Geometry. C. Cambridge University Press, Cambridge (2001)zbMATHGoogle Scholar
  10. 10.
    Martinez, T.: Competitive hebbian learning rule forms perfectly topology preserving maps. In: ICANN (1993)Google Scholar
  11. 11.
    Harris, M.: Optimizing parallel reduction in CUDA. NVIDIA Corporation (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • José García-Rodríguez
    • 1
  • Anastassia Angelopoulou
    • 2
  • Vicente Morell
    • 1
  • Sergio Orts
    • 1
  • Alexandra Psarrou
    • 2
  • Juan Manuel García-Chamizo
    • 1
  1. 1.Dept. of Computing TechnologyUniversity of AlicanteAlicanteSpain
  2. 2.Dept. of Computer Science & Software Engineering (CSSE)University of WestminsterCavendishUnited Kingdom

Personalised recommendations