Advertisement

Neural Computing and Applications

, Volume 31, Supplement 2, pp 1225–1232 | Cite as

Plant disease leaf image segmentation based on superpixel clustering and EM algorithm

  • Shanwen ZhangEmail author
  • Zhuhong You
  • Xiaowei Wu
Original Article

Abstract

Plant disease leaf image segmentation plays an important role in the plant disease detection through leaf symptoms. A novel segmentation method of plant disease leaf image is proposed based on a hybrid clustering. The whole color leaf image is firstly divided into a number of compact and nearly uniform superpixels by superpixel clustering, which can provide useful clustering cues to guide image segmentation to accelerate the convergence speed of the expectation maximization (EM) algorithm, and then, the lesion pixels are quickly and accurately segmented from each superpixel by EM algorithm. The experimental results and the comparison results with similar approaches demonstrate that the proposed method is effective and has high practical value for plant disease detection.

Keywords

Plant disease leaf image segmentation Plant disease detection Superpixel clustering EM algorithm 

Notes

Acknowledgements

This work was partially supported by China National Natural Science Foundation under Grant No. 61473237. It was also supported by the Shaanxi Natural Science Foundation Research Project under Grant No. 2016GY-141. The authors would like to thank all the editors and anonymous reviewers for their constructive advices.

Author contributions

SWZ conceived the algorithm, carried out analyses, prepared the data sets, carried out experiments and wrote the manuscript; ZHY and XWW designed, performed and analyzed experiments and wrote the manuscript; all authors read and approved the final manuscript.

Compliance with ethical standards

Conflicts of interest

The authors declare no conflicts of interest.

References

  1. 1.
    Revathy R, Chennakesavan SA (2015) Threshold based approach for disease spot detection on plant leaf. Trans Eng Sci 3(5):72–75Google Scholar
  2. 2.
    Li Guanlin M, Zhanhong HC et al (2010) Segmentation of color images of grape disease using K_means clustering algorithm. Trans CSAE 26(2):32–37Google Scholar
  3. 3.
    Yuan Y, Li M, Liang Q et al (2011) Segmentation method for crop disease leaf images with complex background. Trans CSAE 27(2):208–212Google Scholar
  4. 4.
    Arivazhagan S, Newlin Shebiah R, Ananthi S et al (2013) Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features. Agric Eng Int: CIGR J 15(1):211–217Google Scholar
  5. 5.
    Gui JS, Hao L, Zhang Q et al (2015) A new method for soybean leaf disease detection based on modified salient regions. Int J Multimed Ubiquitous Eng 10(6):45–52CrossRefGoogle Scholar
  6. 6.
    Al-Hiary H, Bani-Ahmad S, Reyalat M et al (2011) Fast and accurate detection and classification of plant diseases. Int J Comput Appl (0975–8887) 17(1):31–38Google Scholar
  7. 7.
    Yugang R, Jian Z, Miao L et al (2012) Segmentation method for crop disease leaf images based on watershed algorithm. J Comput Appl 32(3):752–755Google Scholar
  8. 8.
    Kaur R, Kang SS (2015) An enhancement in classifier support vector machine to improve plant disease detection. In: IEEE 3rd international conference on innovation and technology in education (MITE), 135–140Google Scholar
  9. 9.
    Chaudhary P, Chaudhari AK, Cheeran AN et al (2012) Color transform based approach for disease spot detection on plant leaf. Int J Comput Sci Telecommun 3(6):65–70Google Scholar
  10. 10.
    Hanping M, Yan cheng Z, Bo H (2008) Segmentation of crop disease leaf images using fuzzy C-means clustering algorithm. Trans CSAE 24(9):136–140Google Scholar
  11. 11.
    Menukaewjinda A, Kumsawat P, Attakitmongcol K (2008) Grape leaf disease detection from color imagery using hybrid intelligent system. In Proceeding of ECT1-CON 14(17) (pp. 513–516). KrabiGoogle Scholar
  12. 12.
    Qin F, Liu D, Sun B et al (2016) Identification of alfalfa leaf diseases using image recognition technology. PLoS ONE 11(12):1–26Google Scholar
  13. 13.
    Baig Mohammad Md, Naga Srujana R, Jaya Naga Jyothi A et al (2016) Disease identification in plants using k-means clustering and gray scale matrices with svm classifier. Int J Appl Sci, Eng Manage 5(2):84–88Google Scholar
  14. 14.
    Qin F, Guo J, Lang F (2015) Superpixel segmentation for polarimatric SAR imagery using local iterative clustering. IEEE Geosci Remote Sens Lett 12(1):13–17CrossRefGoogle Scholar
  15. 15.
    Achanta R, Shaji A, Smith K et al (2012) SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282CrossRefGoogle Scholar
  16. 16.
    Chen Q, Yang XB, Chen YH et al (2014) Image segmentation based on superpixels and saliency. Appl Mech Mater 701–702:312–315CrossRefGoogle Scholar
  17. 17.
    Che X, Zhang F, Zhang R (2017) Medical image segmentation based on SLIC superpixels model. International Conference on Innovative Optical Health Science. 1024502Google Scholar
  18. 18.
    Zhaoxia Fu, Wang Liming (2012) Color image segmentation using mixture Gaussian model and EM Algorithm. Commun Comput Inf Sci 346:61–66Google Scholar
  19. 19.
    Achanta R, Shaji A, Smith K et al (2012) SLIC superpixels compared to state-of the-art superpixel methods. IEEE Trans. Pattern Anal Machine Intell 34(11):2274–2281CrossRefGoogle Scholar
  20. 20.
    Bai XD, Cao ZG, Wang Y et al (2013) Crop segmentation from images by morphology modeling in the CIE L*a*b* color space. Comput Electron Agric 99:21–34CrossRefGoogle Scholar
  21. 21.
    Wu CFJ (1983) On the convergence properties of the EM Algorithm. Ann Stat 11(1):95–103MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Einicke GA, Falco G, Malos JT (2010) EM Algorithm state matrix estimation for navigation. IEEE Signal Process Lett 17(5):437–440CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  1. 1.Department of Information EngineeringXiJing UniversityXi’anChina

Personalised recommendations