Advertisement

Grapevine Nutritional Disorder Detection Using Image Processing

  • D. M. Motiur RahamanEmail author
  • Tintu Baby
  • Alex Oczkowski
  • Manoranjan Paul
  • Lihong Zheng
  • Leigh M. Schmidtke
  • Bruno P. Holzapfel
  • Rob R. Walker
  • Suzy Y. Rogiers
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11854)

Abstract

Vine nutrition is a key element of vineyard management. Nutrient disorders affect vine growth, crop yield, berry composition, and wine quality. Each vineyard may have a unique combination of soil type, vine age, canopy architecture, cultivar and rootstock. Therefore nutritional requirements vary between vineyards and even locations within a vineyard. Nutritional disorders can be detected visually on leaves, fruits, stems or roots. The advancement of image processing and machine learning has made it feasible to develop rapid tools to assess vine nutritional disorders using these symptoms. This paper presents our proposed method of using a smartphone app to capture and analyse images of vine leaves for identifying nutritional disorders of grapevines rapidly and conveniently. Nutrient deficiency/toxicity symptoms were created in hydroponically grown grapevines of both red and white varieties. RGB (red, green, and blue) images of old and young leaves were taken weekly to track the progression of symptoms. A benchmarked dataset was developed through a laboratory based nutrient analysis of the petioles. A wide range of features (e.g., texture, smoothness, contrast and shape) were selected for the following customised machine learning techniques. Our proposed algorithm was developed to identify specific deficiency and toxicity symptoms through training and testing process. The support vector machine has achieved a 98.99% average accuracy in the testing.

Keywords

Nutrition Features Grapevines Viticulture Support vector machine Deficiency 

References

  1. 1.
    Agrios, G.N.: Plant Pathology. Elsevier Academic Press, Amsterdam (2005)Google Scholar
  2. 2.
    Taiz, L., Zeiger, E.: Plant Physiology, vol. 4, pp. 67–86. Sinauer Associates, Sunderland (2006).  https://doi.org/10.1109/icacea.2015.7194375CrossRefGoogle Scholar
  3. 3.
    Bock, C.H., Parker, P.E., Cook, A.Z., Gottwald, T.R.: Characteristics of the perception of different severity measures of citrus canker and the relationships between the various symptom types. Plant Dis. 92, 927–939 (2008).  https://doi.org/10.1094/pdis-92-6-0927CrossRefGoogle Scholar
  4. 4.
    Kaur, S., Pandey, S., Goel, S.: Plants disease identification and classification through leaf images: a survey. Arch. Comput. Methods Eng. 26, 507–530 (2019).  https://doi.org/10.1007/s11831-018-9255-6CrossRefGoogle Scholar
  5. 5.
    Brady, N.C., Weil, R.R.: Instructor’s manual with test item file to accompany The Nature and Properties of Soils, Fourteenth Edition (2008)Google Scholar
  6. 6.
    Fageria, N.K.: Maximizing Crop Yields. Marcel Dekker, New York (1992).  https://doi.org/10.1109/CIS2018.2018.00044CrossRefGoogle Scholar
  7. 7.
    Fageria, N.K., Filho, M.P.B., Moreira, A., Guimarães, C.M.: Foliar fertilization of crop plants. J. Plant Nutr. 32, 1044–1064 (2009).  https://doi.org/10.1080/01904160902872826CrossRefGoogle Scholar
  8. 8.
    Landon, J.R.: A Handbook for Soil Survey and Agricultural Land Evaluation in the Tropics and Subtropics. Taylor & Francis, London (2014)CrossRefGoogle Scholar
  9. 9.
    Nagabhushan, T.N., Aradhya, V.N.M., Jagadeesh, P., Shukla, S., Chaydevi, M.L. (eds.): CCIP 2017. CCIS, vol. 801. Springer, Singapore (2018).  https://doi.org/10.1007/978-981-10-9059-2CrossRefGoogle Scholar
  10. 10.
    Bhange, M., Hingoliwala, H.A.: Smart farming: pomegranate disease detection using image processing. Procedia Comput. Sci. 58, 280–288 (2015).  https://doi.org/10.1016/j.procs.2015.08.022CrossRefGoogle Scholar
  11. 11.
    Shi, Y., Huang, W., Luo, J., Huang, L., Zhou, X.: Detection and discrimination of pests and diseases in winter wheat based on spectral indices and kernel discriminant analysis. Comput. Electron. Agric. 141, 171–180 (2017).  https://doi.org/10.1016/j.compag.2017.07.019CrossRefGoogle Scholar
  12. 12.
    Huang, W., et al.: New optimized spectral indices for identifying and monitoring winter wheat diseases. IEEE J. Sel. Top Appl. Earth Obs. Remote Sens. 7, 2516–2524 (2014).  https://doi.org/10.1109/JSTARS.2013.2294961CrossRefGoogle Scholar
  13. 13.
    Jhuria, M., Kumar, A., Borse, R.: Image processing for smart farming: detection of disease and fruit grading. In: IEEE 2nd International Conference on Image Information Process, ICIIP 2013, pp. 521–526. IEEE (2013).  https://doi.org/10.1109/ICIIP.2013.6707647
  14. 14.
    Husin, Z., Bin Md Shakaff, A.Y., Bin Abdul Aziz, A.H., Bin Mohamed Farook, R.B.S.: Feasibility study on plant chili disease detection using image processing techniques. In: Proceedings of the 3rd International Conference on Intelligent Systems Modelling and Simulation, ISMS 2012, pp. 291–296 (2012)  https://doi.org/10.1109/ISMS.2012.33
  15. 15.
    Badnakhe, M.R.: Infected leaf analysis and comparison by Otsu threshold and k-means clustering. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 2, 449–452 (2012)Google Scholar
  16. 16.
    Al Hiary, H., Bani Ahmad, S., Reyalat, M., Braik, M., ALRahamneh, Z.: Fast and accurate detection and classification of plant diseases. Int. J. Comput. Appl. 17, 31–38 (2011)Google Scholar
  17. 17.
    Zhang, C., Wang, X., Li, X.: Design of monitoring and control plant disease system based on DSP&FPGA. In: 2nd International Conference on Networks Security, Wireless Communications and Trusted Computing, NSWCTC 2010, vol. 2, pp. 479–482 (2010).  https://doi.org/10.1109/NSWCTC.2010.246
  18. 18.
    Phadikar, S., Sil, J.: Rice disease identification using pattern recognition techniques. In: Proceedings of the 11th International Conference on Computer and Information Technology, ICCIT 2008, pp. 420–423 (2008).  https://doi.org/10.1109/ICCITECHN.2008.4803079
  19. 19.
    Kiaee, N., Hashemizadeh, E., Zarrinpanjeh, N.: Using GLCM features in Haar wavelet transformed space for moving object classification. IET Intell. Transp. Syst. 13, 1148–1153 (2019).  https://doi.org/10.1049/iet-its.2018.5192CrossRefGoogle Scholar
  20. 20.
    Sun, W., Zeng, N., He, Y.: Morphological Arrhythmia automated diagnosis method using gray-level co-occurrence matrix enhanced convolutional neural network. IEEE Access 7, 67123–67129 (2019).  https://doi.org/10.1109/ACCESS.2019.2918361CrossRefGoogle Scholar
  21. 21.
    Shoumy, N.J., Ang, L.-M., Motiur Rahaman, D.M.: Multimodal big data affective analytics. In: Seng, K.P., Ang, L.-M., Liew, A.W.-C., Gao, J. (eds.) Multimodal Analytics for Next-Generation Big Data Technologies and Applications, pp. 45–71. Springer, Cham (2019).  https://doi.org/10.1007/978-3-319-97598-6_3CrossRefGoogle Scholar
  22. 22.
    Paul, M., Musfequs Salehin, M.: Spatial and motion saliency prediction method using eye tracker data for video summarization. IEEE Trans. Circ. Syst. Video Technol. 29, 1856–1867 (2019).  https://doi.org/10.1109/TCSVT.2018.2844780CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • D. M. Motiur Rahaman
    • 1
    Email author
  • Tintu Baby
    • 1
  • Alex Oczkowski
    • 1
  • Manoranjan Paul
    • 1
    • 2
  • Lihong Zheng
    • 1
    • 3
  • Leigh M. Schmidtke
    • 1
  • Bruno P. Holzapfel
    • 1
    • 4
  • Rob R. Walker
    • 1
    • 5
  • Suzy Y. Rogiers
    • 1
    • 4
  1. 1.National Wine and Grape Industry CentreCharles Sturt UniversityWagga WaggaAustralia
  2. 2.School of Computing and MathematicsCharles Sturt UniversityBathurstAustralia
  3. 3.School of Computing and MathematicsCharles Sturt UniversityWagga WaggaAustralia
  4. 4.NSW Department of Primary IndustriesWagga WaggaAustralia
  5. 5.Commonwealth Scientific and Industrial Research OrganisationAdelaideAustralia

Personalised recommendations