access icon free Semi-automatic leaf disease detection and classification system for soybean culture

© The Institution of Engineering and Technology
Received 03/08/2017, Accepted 28/01/2018, Revised 24/11/2017, Published 01/02/2018

Development of automatic disease detection and classification system is significantly explored in precision agriculture. In the past few decades, researchers have studied several cultures exploiting different parts of a plant. A similar study is performed for Soybean using leaf images. A rule based semi-automatic system using concepts of k-means is designed and implemented to distinguish healthy leaves from diseased leaves. In addition, a diseased leaf is classified into one of the three categories (downy mildew, frog eye, and Septoria leaf blight). Experiments are performed by separately utilising colour features, texture features, and their combinations to train three models based on support vector machine classifier. Results are generated using thousands of images collected from PlantVillage dataset. Acceptable average accuracy values are reported for all the considered combinations which are also found to be better than existing ones. This study also attempts to discover the best performing feature set for leaf disease detection in Soybean. The system is shown to efficiently compute the disease severity as well. Visual examination of leaf samples further proves the suitability of the proposed system for detection, classification, and severity calculation.

Inspec keywords: support vector machines; food products; agricultural engineering; image colour analysis; image classification; feature extraction; image texture; plant diseases

Other keywords: precision agriculture; semiautomatic leaf disease detection and classification system; support vector machine classifier; PlantVillage dataset; leaf image; k-means concepts; colour feature; feature set; texture feature; soybean culture; automatic disease detection and classification system

Subjects: Image recognition; Agriculture, forestry and fisheries computing; Computer vision and image processing techniques; Products and commodities; Agriculture; Knowledge engineering techniques; Industrial applications of IT

References

    1. 1)
      • 27. Mistry, Y., Ingole, D.T., Ingole, M.D.: ‘Content based image retrieval using hybrid features and various distance metric’, J. Electr. Syst. Inf. Technol., 2017, article in press, doi: http://dx.doi.org/10.1016/j.jesit.2016.12.009.
    2. 2)
      • 14. Gharge, S., Singh, P.: ‘Image processing for soybean disease classification and severity estimation’, in Shetty, N., Prasad, N., Nalini, N. (Eds.): ‘Emerging research in computing, information, communication and applications’ (Springer, New Delhi, India, 2016), pp. 493–500.
    3. 3)
      • 33. Yu, H., Kim, S.: ‘SVM tutorial-classification, regression and ranking’, in Rozenberg, G., Bäck, T., Kok, J.N. (Eds.): ‘Handbook of natural computing’ (Springer, Berlin Heidelberg, 2012), pp. 479–506.
    4. 4)
      • 18. Jadhav, S.B., Patil, S.B.: ‘Grading of soybean leaf disease based on segmented image using k-means clustering’, Int. J. Adv. Res. Electron. Commun. Eng., 2015, 4, (6), pp. 1816–1822.
    5. 5)
      • 34. Kaur, S., Pandey, S., Goel, S.: ‘An automatic leaf disease detection system for legume species’, J. Biol. Today's World, 2017, 6, pp. 115–122.
    6. 6)
      • 31. Yadav, R., Anand, R.S., Dewal, M.L., et al: ‘Performance analysis of discrete wavelet transform based first-order statistical texture features for hardwood species classification’, Procedia Comput. Sci., 2015, 57, pp. 214–221.
    7. 7)
      • 4. ‘Signs and symptoms of plant disease: Is it fungal, viral or bacterial?’, available at http://msue.anr.msu.edu/news/signs_and_symptoms_of_plant_disease_is_it_fungal_viral_or_bacterial, accessed January 2017.
    8. 8)
      • 28. Haralick, R.M., Shanmugam, K., Dinstein, I.: ‘Textural features for image classification’, Trans. Syst. Man Cybern., 1973, 3, (6), pp. 610–621.
    9. 9)
      • 3. ‘Diagnosing plant problems: plant diseases and disorders’, available at https://firstdetector.org/static/pdf/NPDNDiagnosingPlantProblemsPlantDiseaseforreview2.pdf, accessed February 2017.
    10. 10)
      • 13. Shrivastava, S., Singh, S.K., Hooda, D.S.: ‘Statistical texture and normalized discrete cosine transform-based automatic soya plant foliar infection cataloguing’, Br. J. Math. Comput. Sci., 2014, 4, (20), pp. 2901–2916.
    11. 11)
      • 20. ‘Hunter lab color scale’, Insight on Color, Hunter Labs Reston, 1996, 8, (9), pp. 1–4, available at https://support.hunterlab.com/hc/en-us/article_attachments/201440625/an08_96a2.pdf.
    12. 12)
      • 8. ‘Characteristics of soybean foliar diseases from bacterial blight to rust’, available at http://extension.cropsciences.illinois.edu/fieldcrops/classics/2005/characteristicsofsoybeandiseases.php, accessed January 2017.
    13. 13)
      • 15. Dandawate, Y., Kokare, R.: ‘An automated approach for classification of plant diseases towards development of futuristic decision support system in Indian perspective’. Proc. IEEE Int. Conf. Advances in Computing, Communications and Informatics (ICACCI), Kerala, India, August 2015, pp. 794–799.
    14. 14)
      • 35. ‘IPM Images’, available at https://www.ipmimages.org/, accessed January 2017.
    15. 15)
      • 30. Cheng, F.H., Chen, Y.L.: ‘Real time multiple objects tracking and identification based on discrete wavelet transform’, Pattern Recognit., 2006, 39, pp. 1126–1139.
    16. 16)
      • 21. Wang, X., Hänsch, R., Ma, L., et al: ‘Comparison of different color spaces for image segmentation using graph-cut’. Proc. IEEE Int. Conf. in Computer Vision Theory and Applications (VISAPP), January 2014, pp. 301–308.
    17. 17)
      • 5. Li, X., Yang, X.B.: ‘Similarity, pattern, and grouping of soybean fungal diseases in the United States: implications for the risk of soybean rust’, Plant Dis., 2009, 93, (2), pp. 162–169.
    18. 18)
      • 19. Pujari, J.D., Yakkundimath, R.S., Jahagirdar, S., et al: ‘Quantitative detection of soybean rust using image processing techniques’, J. Crop Prot., 2015, 5, (1), pp. 75–87.
    19. 19)
      • 32. Amsaveni, V., Singh, N.A., Dheeba, J.: ‘Application of support vector machine classifier for computer aided diagnosis of brain tumor from MRI’. Proc. Int. Conf. on Swarm, Evolutionary, and Memetic Computing, Bhubaneswar, India, December 2014, pp. 514–522.
    20. 20)
      • 16. Barbedo, J.G.A., Godoy, C.V.: ‘Automatic classification of soybean diseases based on digital images of leaf symptoms’. SBI AGRO, October 2015.
    21. 21)
      • 17. Shrivastava, S., Singh, S.K., Hooda, D.S.: ‘Color sensing and image processing-based automatic soybean plant foliar disease severity detection and estimation’, Multimedia Tools Appl., 2015, 74, (24), pp. 11467–11484.
    22. 22)
      • 9. ‘Soybean diseases’, available at https://alliedcooperative.files.wordpress.com/2014/07/soybeandiseases.pdf, accessed January 2017.
    23. 23)
      • 26. Huang, J.: ‘Color-spatial image indexing and applications’. PhD thesis, Cornell University, 1998.
    24. 24)
      • 24. Gavhale, K.R., Gawande, U.: ‘An overview of the research on plant leaves disease detection using image processing techniques’, IOSR J. Comput. Eng., 2014, 16, (1), pp. 10–16.
    25. 25)
      • 1. ‘Nitrogen fixation’, available at https://en.wikipedia.org/wiki/Nitrogen_fixation, accessed February 2017.
    26. 26)
      • 2. Savary, S., Ficke, A., Aubertot, J.-N., et al: ‘Crop losses due to diseases and their implications for global food production losses and food security’, Food Secur., 2012, 4, (4), pp. 519–537.
    27. 27)
      • 6. ‘Soybean growth and development’, available at http://corn.agronomy.wisc.edu/Crops/Soybean/pdfs/L004.pdf, accessed February 2017.
    28. 28)
      • 12. Shrivastava, S., Hooda, D.S.: ‘Automatic brown spot and frog eye detection from the image captured in the field’, Am. J. Intell. Syst., 2014, 4, (4), pp. 131–134.
    29. 29)
      • 29. Manjunath, B.S., Ma, W.Y.: ‘Texture features for browsing and retrieval of image data’, IEEE Trans. Pattern Anal. Mach. Intell., 1996, 18, (8), pp. 837–842.
    30. 30)
      • 23. Spath, H.: ‘Cluster dissection and analysis: theory, FORTRAN programs, examples’, translated by J. Goldschmidt (Halsted Press, New York, 1985).
    31. 31)
      • 37. Cai, J., Miklavcic, S.: ‘Automated extraction of three-dimensional cereal plant structures from two-dimensional orthographic images’, IET Image Process., 2012, 6, (6), pp. 687–696.
    32. 32)
      • 7. Mian, M.A., Missaoui, A.M., Walker, D.R., et al: ‘Frogeye leaf spot of soybean: a review and proposed race designations for isolates of Cercospora sojina Hara’, Crop Sci., 2008, 48, (1), pp. 14–24.
    33. 33)
      • 36. Barbedo, J.G.A.: ‘A review on the main challenges in automatic plant disease identification based on visible range images’, Biosyst. Eng., 2016, 144, pp. 52–60.
    34. 34)
      • 11. Hughes, D.P., Salathé, M.: ‘An open access repository of images on plant health to enable the development of mobile disease diagnostics’, 2015 CoRR abs/1511.08060.
    35. 35)
      • 25. Sachdeva, J., Kumar, V., Gupta, I., et al: ‘A package-SFERCB-segmentation, feature extraction, reduction and classification analysis by both SVM and ANN for brain tumors’, Appl. Soft Comput., 2016, 47, pp. 151–167.
    36. 36)
      • 22. Seber, G.A.F.: ‘Multivariate observations’ (Wiley, New York, 1984).
    37. 37)
      • 10. Giesler, L.J.: ‘Frog eye leaf spot of soybean’, available at http://extensionpublications.unl.edu/assets/pdf/g2213.pdf, accessed February 2017.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2017.0822
Loading

Related content

content/journals/10.1049/iet-ipr.2017.0822
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading