CNN Based High Performance Computing for Real Time Image Processing on GPU

  • Sasanka Potluri
  • Alireza Fasih
  • Laxminand Kishore Vutukuru
  • Fadi Al Machot
  • Kyandoghere Kyamakya
Part of the Studies in Computational Intelligence book series (SCI, volume 391)


Many of the basic image processing tasks suffer from processing overhead to operate over the whole image. In real time applications the processing time is considered as a big obstacle for its implementations. A High Performance Computing (HPC) platform is necessary in order to solve this problem. The usage of hardware accelerator make the processing time low. In recent developments, the Graphics Processing Unit (GPU) is being used in many applications. Along with the hardware accelerator a proper choice of the computing algorithm makes it an added advantage for fast processing of images. The Cellular Neural Network (CNN) is a large-scale nonlinear analog circuit able to process signals in real time [1]. In this paper, we develop a new design in evaluation of image processing algorithms on the massively parallel GPUs with CNN implementation using Open Computing Language (OpenCL) programming model. This implementation uses the Discrete Time CNN (DT-CNN) model which is derived from originally proposed CNN model. The inherent massive parallelism of CNN along with GPUs makes it an advantage for high performance computing platform [2]. The advantage of OpenCL makes the design to be portable on all the available graphics processing devices and multi core processors. Performance evaluation is done in terms of execution time with both device (i.e. GPU) and host (i.e. CPU).


Graphic Processing Unit Cellular Neural Network Image Processing Algorithm Image Processing Application Hardware Accelerator 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Montufar-Chaveznava, R., Guinea, D.: A Cellular Neural Network System for Real-Time Image Processing. In: MED 2003 - The 11th Mediterranean Conference on Control and Automation, 3rd edn. (2003)Google Scholar
  2. 2.
    Fernandez, A., et al.: Cellular neural networks simulation on a parallel graphics processing unit, 3rd edn., pp. 208–212 (2008)Google Scholar
  3. 3.
    Kanwar, R.: Real-Time Edge Detection using Sundance Video and Image Processing System, 3rd edn. (2009)Google Scholar
  4. 4.
    Greco, J.: Parallel Image Processing and Computer Vision Architecture, 3rd edn., Citeseer (2005)Google Scholar
  5. 5.
    Choudhary, A., Ranka, S.: Guest editor’s introduction: parallel processing for computer vision and image understanding. In: Computer, vol. 25(2), pp. 7–10 (1992)Google Scholar
  6. 6.
    Athanas, P.M., Abbott, A.L.: Real-time image processing on a custom computing platform. In: EComputer, 3rd edn., vol. 28(2), pp. 16–25 (2002)Google Scholar
  7. 7.
    Wang, X., Ziavras, S.G.: KHERA: A reconfigurable and mixed-mode parallel computing engine on platform FPGAs. Citeseer (2004)Google Scholar
  8. 8.
    Tonde, C.: Hardware and software platforms for computer vision, 3rd edn.Google Scholar
  9. 9.
    Yang, Z., Nishio, Y., Ushida, A.: A Two Layer CNN in Image Processing ApplicationsGoogle Scholar
  10. 10.
    Tsuchiyama, R., et al.: The OpenCL Programming Book. Fixstars CorporationGoogle Scholar
  11. 11.
    Barak, A., et al.: A Package for OpenCL Based Heterogeneous Computing on Clusters with Many GPU DevicesGoogle Scholar
  12. 12.
    Nossek, J.A., et al.: Cellular neural networks: Theory and circuit design. International Journal of Circuit Theory and Applications 20(5), 533–553 (1992)CrossRefGoogle Scholar
  13. 13.
    Chua, L.O., Roska, T.: Cellular neural networks and visual computing: foundation and applications. Cambridge Univ. Pr. (2002)Google Scholar
  14. 14.
    Chua, L.O., Roska, T.: The CNN paradigm. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications 40(3), 147–156 (2002)CrossRefGoogle Scholar
  15. 15.
    Kawahara, M., Inoue, T., Nishio, Y.: Image processing application using CNN with dynamic template. IEEEGoogle Scholar
  16. 16.
    Takenouchi, H., Watanabe, T., Hideki, A.: Development of DT-CNN Emulator Based on GPGPUGoogle Scholar
  17. 17.
    Malki, S., Spaanenburg, L., Ray, N.: Image stream processing on a packet-switched discrete-time CNN (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Sasanka Potluri
    • 1
  • Alireza Fasih
    • 1
  • Laxminand Kishore Vutukuru
    • 1
  • Fadi Al Machot
    • 1
  • Kyandoghere Kyamakya
    • 1
  1. 1.Institute of Smart System Technologies, Transportation Informatics GroupAlpen-Adria-University KlagenfurtKlagenfurtAustria

Personalised recommendations