Quaternion Based Thermal Condition Monitoring System

  • Wai Kit Wong
  • Chu Kiong Loo
  • Way Soong Lim
  • Poi Ngee Tan
Part of the Proceedings in Information and Communications Technology book series (PICT, volume 2)


In this paper, we will propose a new and effective machine condition monitoring system using log-polar mapper, quaternion based thermal image correlator and max-product fuzzy neural network classifier. Two classification characteristics namely: peak to sidelobe ratio (PSR) and real to complex ratio of the discrete quaternion correlation output (p-value) are applied in the proposed machine condition monitoring system. Large PSR and p-value observe in a good match among correlation of the input thermal image with a particular reference image, while small PSR and p-value observe in a bad/not match among correlation of the input thermal image with a particular reference image. In simulation, we also discover that log-polar mapping actually help solving rotation and scaling invariant problems in quaternion based thermal image correlation. Beside that, log-polar mapping can have a two fold of data compression capability. Log-polar mapping can help smoother up the output correlation plane too, hence makes a better measurement way for PSR and p-values. Simulation results also show that the proposed system is an efficient machine condition monitoring system with accuracy more than 98%.


Reference Image Thermal Image Invariant Problem Thermal Camera Fuzzy Relational Equation 
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.
    Chaudhuri, P., Sentra, P., Yoele, S., Prakesh, A.: et al: Non-destructive evaluation of brazed joints between cooling tube and heat sink by IR thermography and its verification using FE analysis. NDT & E International 39(2), 88–95 (2006)CrossRefGoogle Scholar
  2. 2.
  3. 3.
  4. 4.
  5. 5.
    Weiman, C.: Log-polar vision for mobile robot navigation. In: Proc. of Electronic Imaging Conferences, Boston, USA, November 1990, pp. 382–385 (1990)Google Scholar
  6. 6.
    Jurie, F.: A new log-polar mapping for space variant imaging: Application to face detection and tracking. Pattern Recognition 32(55), 865–875 (1999)CrossRefGoogle Scholar
  7. 7.
    Berton, F.: A brief introduction to log-polar mapping. Technical report, LIRA-Lab, University of Genova (February 2006)Google Scholar
  8. 8.
    Hamilton, W.R.: Elements of Quaternions. Longmans/Green, London/U.K (1866)Google Scholar
  9. 9.
    Xie, C., Savvides, M., Kumar, B.V.K.V.: Quaternion correlation filters for face recognition in wavelet domain. In: Int. Conf. on Accoustic, Speech and Signal Processing, ICASSP 2005, pp. II85–II88 (2005)Google Scholar
  10. 10.
    Pei, S.C., Ding, J.J., Chang, J.: Color pattern recognition by quaternion correlation. In: Proc. of Int. Conf. on Image Processing, vol. 1, pp. 894–897 (2001)Google Scholar
  11. 11.
    Moxey, C.E., Sangwine, S.J., Ell, T.: Hypercomplex correlation techniques for vector images. IEEE Trans. on Signal Processing 51(7), 1941–1953 (2003)CrossRefMathSciNetGoogle Scholar
  12. 12.
    Bourke, M.M., Fisher, D.G.: Solution algorithms for fuzzy relational equations with max-product composition. Fuzzy Sets Systems 94, 61–69 (1998)CrossRefMathSciNetMATHGoogle Scholar
  13. 13.
    Xiao, P., Yu, Y.: Efficient learning algorithm for fuzzy max-product associative memory networks. In: Proc. SPIE, vol. 3077, pp. 388–395 (1997)Google Scholar
  14. 14.
    Owen, J., Hunter, A., Fletcher, E.: A fast model-free morphology-based object tracking algorithm. In: British Machine Vision Conference, pp. 767–776 (2002)Google Scholar

Copyright information

© Springer Tokyo 2010

Authors and Affiliations

  • Wai Kit Wong
    • 1
  • Chu Kiong Loo
    • 1
  • Way Soong Lim
    • 1
  • Poi Ngee Tan
    • 1
  1. 1.Faculty of Engineering and TechnologyMultimedia UniversityJln Ayer Keroh LamaMalaysia

Personalised recommendations