Interpretation of Sound Tomography Image for the Recognition of Ganoderma Infection Level in Oil Palm

  • Mohd Su'ud Mazliham
  • Pierre Loonis
  • Abu Seman Idris
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 6)

Basal stem rot (BSR) disease in oil palm caused by a group of decaying fungi called Ganoderma is considered as the most serious disease faced by the oil palm plantations in SouthEast Asia [1]. Significant yield losses can be observed when the number of palms infected by the fungus increases in the plantation as the infected palms will produce less quality fruit and eventually die thus requiring an early replanting.

In this framework, we suggest a system capable of identifying Ganoderma infection inside the palm stem and localizing the infected area. The identification of the infection is based on developing expert’s rules to identify the presence of Ganoderma fungus in the palm stem based on the recognition of the lesion in the stem using tomography images. These rules will enable us to perform automatic detection directly on the plantation.

The results of this study are presented as follows. Section 29.2 is devoted to the presentation of the expert’s current knowledge of the Ganoderma infection pattern in the palm stem. The analysis of tomography images based on the sound propagation in the stem to detect abnormalities in the stem is presented in Sect. 29.3. A fuzzy inference system classifying each suspected lesion pattern observed in the tomography image using rules established with the help from experts and the lesion features extracted from the tomography images into three possible hypotheses: Ganoderma infection (G), non-Ganoderma infection (N), or intact stem tissue (I) is proposed in Sect. 29.4. The result of this classification is presented in Sect. 29.5. The result is then used to generate a basic probability assignment or mass function of lesion condition according to the above-mentioned hypotheses in Sect. 29.6. Section 29.7 discusses the method to obtain overall oil palm health condition belief function through the combination of data obtained in each lesion observed in the stem.


Membership Function Fuzzy Inference System Tomography Image Mass Function Initialization Sonic Tomography 
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.
    Idris AS and Ariffin D. Ganoderma penyakit reput pangkal batang dan kawalannya. Risalah Sawit, No. 11, 2003.Google Scholar
  2. 2.
    Flood J, Keenan L, Wayne S, and Hasan Y. Studies on oil palm trunks as sources of infection in the field. Mycapathologia, (19):101–107, 2005.CrossRefGoogle Scholar
  3. 3.
    Idris AS, Ismail S, Ariffin D, and Ahmad H. Prolonging the productive life of ganoderma infected palms with hexaconazole. MPOB Information Series, 2004.Google Scholar
  4. 4.
    Arifin D and Idris AS. The ganoderma selective medium. MPOB Information-Series, 1992.Google Scholar
  5. 5.
    Idris AS, Yamaoka M, Hayakawa S, Basri MW, Noorhashimah I, and Ariffin, D. Pcr technique for detection of ganoderma, mpob information. MPOB Information, Series TT No. 188, 2003.Google Scholar
  6. 6.
    Turner PD. Palm Oil Diseases and Disorers. Oxford University Press, 1981.Google Scholar
  7. 7.
    Ariffin D, Idris AS, and Abdul Halim H. Significance of the balack line within oil palm tissue decayed by ganoderma boninense. Elaeis, 1(1), 1989.Google Scholar
  8. 8.
    Schwarze and Fermer. Ganoderma on tree—differentiation of species and studies of invasiveness. available online
  9. 9.
    Elliott ML and Broschat TK. Ganoderma butt rot of palms., 2000. University of Florida, Institute of Food and Agricultural Science.
  10. 10.
    Steffen R. A new tomographic device for the non destructive testing of trees. 2000.Google Scholar
  11. 11.
    Sandoz JL. Ultrasonic solid wood evaluation in industrial application. 10th International Symposium on Nondestructive Testing of Wood, 1996.Google Scholar
  12. 12.
    Veres IA and Sayir MB. Wave propogation in a wooden bar. Ultrasonic Elsevier, 2004.Google Scholar
  13. 13.
    L. Iancu et al. Quantification of defects in wood by use of ultrasonic in association with imagistic method. 15t WCNDT Roma, 2000.Google Scholar
  14. 14.
    T. Tanaka. Wood inspection thermography. Wood NDT, 2000.Google Scholar
  15. 15.
    Nicolotti G, Socco LV, Martinis R, Godio A, and Sambuelli L. Application and comparison of tree tomographic techniques for detection of decay in trees. Journal of Arboriculture, 29(2):66–78, March 2003.Google Scholar
  16. 16.
    Schwarze F.W.M.R, Rabe C, Ferner D, and Fink S. Detection of decay in trees with stress waves and interpretation of acoustic tomograms. Arboricultural Journal, 28(1/2):3–19, 2004.Google Scholar
  17. 17.
    Gonzalez RC and Woods RE. Digital Image Processing (2nd Edition). Addison-Wesley, Reading, MA, 2002.Google Scholar
  18. 18.
    Mazliham MS, Loonis P, and Idris AS. Extraction of information based on experts knowledge rules to recognize ganoderma infection in tomography image. In Proceedings of IAENG International MultiConference of Engineers and Computer Scientists, Hong Kong. IAENG, 2007.Google Scholar
  19. 19.
    Nelson BN. Automatic vehicle detection in infrared imagery using a fuzzy inference-based classification system. IEEE Transaction on Fuzzy Systems, 9(1), February 2001.Google Scholar
  20. 20.
    Aydin. Fuzzy set approaches to classification of rock masses. Engineering Geology, (74):227–245, 2004.CrossRefGoogle Scholar
  21. 21.
    Mazliham MS, Loonis P, and Idris AS. Towards automatic recognition and grading of ganoderma infection pattern using fuzzy systems. In ENFORMATIKA Transaction on Engineering, Computing and Technology Advances in Computer, Infromation and Systems Science and Engineering, Vol 19, Bangkok, 2007.Google Scholar
  22. 22.
    Germain M, Voorons M, Boucher JM, and Benie GB. Fuzzy statistical classification method for multiband image fusion. In ISIF, 2002.Google Scholar
  23. 23.
    Straszecka E. An interpretation of focal elements as fuzzy sets. International Journal of Intelligent Systems, 18:821–835, 2003.MATHCrossRefGoogle Scholar
  24. 24.
    Bentabet L, Zhu YM, Dupuis O, Kaftandjian V, Babot D, and Rombaut M. Use of clustering or determining mass function Dempster Shafer theory. In 5th International Conference on ICSP, 2000.Google Scholar
  25. 25.
    Mazliham MS, Loonis P, and Idris AS. Mass function initialization rules for ganoderma infection detection by tomography sensor. In Proceedings of Second IASTED International Conference on Computer Intelligence, San Francisco. IASTED, 2006.Google Scholar
  26. 26.
    Sadiq R and Rodriguez MJ. Interpreting drinking water quality in the distribution system using dempster shafer theory of evidence. Chemosphere, 59(2):177–188, 2005.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Mohd Su'ud Mazliham
    • 1
    • 2
  • Pierre Loonis
    • 2
  • Abu Seman Idris
    • 3
  1. 1.Universiti Kuala LumpurSelangorMalaysia
  2. 2.Laboratoire Informatique Image InteractionUniversite de La RochelleFrance
  3. 3.Malaysia Palm Oil Board No. 6Persiaran InstitusiBandar Baru BangiMalaysia

Personalised recommendations