Advertisement

Region Identification of Infected Rice Images Using the Concept of Fermi Energy

  • Santanu Phadikar
  • Jaya Sil
  • Asit KumarDas
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 177)

Abstract

Automated disease detection using the features of infected regions of a diseased plant image is a growing field of research in precision agriculture. Usually, infected regions are identified by applying different threshold based segmentation techniques. However, due to various factors like non-uniform illumination or noises, these techniques fail to provide sufficient information for classifying diseases accurately. In the paper, a novel region identification method based on Fermi energy has been proposed to detect the infected portion of the diseased rice images. From the infected region, neighboring gray level dependence matrix (NGLDM) based texture features are extracted to classify different diseases of rice plants. Performance of the proposed method has been evaluated by comparing classification accuracy with other segmentation algorithms, demonstrating superior result.

Keywords

Fermi Energy Disease Classification Region Detection Feature Extraction 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Sing, A.K.: Advances in Data Analytical Techniques, vol. VI, pp. 165–174. Indian Agricultural Statistics Research InstituteGoogle Scholar
  2. 2.
    Ray, N., Saha, B.N.: Edge Sensitive Variational Image Thresholding. In: ICIP, vol. VI, pp. 37–40 (2007)Google Scholar
  3. 3.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Pearson Education, New Delhi (2007)Google Scholar
  4. 4.
    Sankur, B., Sezgin, M.: Survey over image thresholding techniques and quantitative performance evaluation. Electron Imaging 13(1), 146–165 (2004)CrossRefGoogle Scholar
  5. 5.
    Trier, O.D., Jain, A.K.: Goal-directed evaluation of binarization methods. IEEE Tran. Pattern Analysis and Machine Intelligence PAMI-17, 1191–1201 (1995)CrossRefGoogle Scholar
  6. 6.
    Guo, R., Pandit, S.M.: Automatic threshold selection based on histogram modes and a discriminant criterion. Machine Vision and Applications 10, 331–338 (1998)CrossRefGoogle Scholar
  7. 7.
    Cai, J., Liu, Z.Q.: A New Thresholding Algorithm Based on All-Pole Model. In: ICPR 1998, Int. Conf. on Pattern Recognition, Australia, pp. 34–36 (1998)Google Scholar
  8. 8.
    Cho, S., Haralick, R., Yi, S.: Improvement of Kittler and Illingworths’s Minimum Error Thresholding. Pattern Recognition 22, 609–617 (1989)CrossRefGoogle Scholar
  9. 9.
    Jawahar, C.V., Biswas, P.K., Ray, A.K.: Investigations on fuzzy thresholding based on fuzzy clustering. Pattern Recognition 30(10), 1605–1613 (1997)MATHCrossRefGoogle Scholar
  10. 10.
    Li, C.H., Tam, P.K.S.: An Iterative Algorithm for Minimum Cross-Entropy Thresholding. Pattern Recognition Letters 19, 771–776 (1998)MATHCrossRefGoogle Scholar
  11. 11.
    Savakis, A.: Adaptive document image thresholding using foreground and background clustering. In: ICIP 1998: Int. Conf. On Image Processing, Chicago (October 1998)Google Scholar
  12. 12.
    Cheng, S.C., Tsai, W.H.: A Neural Network Approach of the Moment-Preserving Technique and Its Application to Thresholding. IEEE Trans. Computers (42), 501–507 (1993)CrossRefGoogle Scholar
  13. 13.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models: IJCV, pp. 321–331 (1987)Google Scholar
  14. 14.
    Caselles, V., Kimme, R.: Minimal Surfaces Based Object Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(4), 394–398 (1997)CrossRefGoogle Scholar
  15. 15.
    Xavier, B., Pierre, V., Jean-Philippe, T.: A priori information in image segmentation: energy functionalbased oh’ shape statistical model and image information. IEEE (2003)Google Scholar
  16. 16.
    Hummel, R.E.: Electronic Properties of Materials (6), 63–74 (2011)Google Scholar
  17. 17.
    Wei, G., Sammes, N.M.: An introduction to electronic and ionic materials (3), 41–44 (2000)Google Scholar
  18. 18.
    Chaoxin, Z., Da-Wen, S., Liyun, Z.: Recent applications of image texture for evaluation of food qualities—a review. Trends in Food Science & Technology 17, 113–128 (2006)CrossRefGoogle Scholar
  19. 19.
    Otsu, N.: A Threshold Selection Method from Gray Level Histograms. IEEE Transaction on Systems, Man and Cybernetics 9, 62–66 (1979)CrossRefGoogle Scholar
  20. 20.
    MacQueen, J.B.: Some Methods for classification and Analysis of Multivariate Observations. In: Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability, pp. 281–297. University of California Press (1967)Google Scholar
  21. 21.
    WEKA, Machine Learning Software (2011), http://www.cs.waikato.ac.nz/~ml/
  22. 22.
    Ou, S.H.: Rice Diseases,England: Commonwealth Mycological Institute (1972)Google Scholar
  23. 23.
    Webster, R.K.: Rice blast disease identification guide. University of California, Davis (2000)Google Scholar
  24. 24.
    Rice Doctor, International Rice Research Institute, Philipines (2003), http://www.irri.org

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Santanu Phadikar
    • 1
  • Jaya Sil
    • 2
  • Asit KumarDas
    • 2
  1. 1.Department of Computer Science and EngineeringWest Bengal University of TechnologyKolkataIndia
  2. 2.Department of Computer Science and TechnologyBengal Engineering and Science UniversityHowrahIndia

Personalised recommendations