An Automated Model to Measure the Water Content of Leaves

  • I. A. Wagachchi
  • B. B. D. S. Abeykoon
  • R. D. K. Rassagala
  • D. P. Jayathunga
  • T. KartheeswaranEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1037)


Leafy product industries like tea, tobacco, Palmyra, green vegetables, Ayurveda productions are playing significant role to uplift the Sri Lankan economy. The current water content in the leaves is an essential factor for leafy productions to maintain their quality. Naked eye observation of an expert is the general method to identify the water content. The objective of this study is to introduce a novel and easy method to measure the water content of the detached plant leaves using digital image processing. As a result, a simple computational water content prediction method has been built using image processing techniques to obtain a quality output at the end of production processes. The findings of this study help to identify the water content without an expert in an efficient manner. First, the color images were captured in a controlled environment from the drying leaves and simultaneously the weight was measured traditionally to find the water loss. Several features of the images have been analyzed to find the best features which show a better correlation with the changes of the water content in the leaves. The textural and statistical features were extracted. The green matrix of the RGB image is taken for feature extraction to get the better results. The best features among the selected features are chosen through a correlation test. The classification was done with the K-Nearest Neighbor algorithm by training with the selected best features of the training set of images. Finally, a simple model was built using the significant features which have a relationship with the water content measurement. Accuracy has been achieved at a satisfactory level, and the model derived can be used to predict the water content of a particular green leaf (dried leaf also) through images. This model will be a turning point for measuring the water content of the leaves in the industries.


Image processing Water content KNN 


  1. 1.
    Leiva, L., Acosta, N. (n.d.): Quantization of moisture content in Yerba Mate leaves through image processingGoogle Scholar
  2. 2.
    Liang, G., et al.: Prediction of moisture content for congou black tea withering leaves using image features and nonlinear method. Sci. Rep. 8, 1–22 (2018).
  3. 3.
    Schweiggert, U., Carle, R., Schieber, A.: Conventional and alternative processes for spice production-a review. Trends Food Sci. Technol. 18, 260–268 (2007)CrossRefGoogle Scholar
  4. 4.
    Crivelli, G., Nani, R.C., Di Cesare, L.F.: Influence of processing on the quality of dried herbs. In: Atti VI Giornatescientifiche SOI, Spoleto, 23–25 April 2002, vol. II, pp. 463–464 (2002)Google Scholar
  5. 5.
    Pattanashetti, I.I., Galagali, P.M.N.: Attenuation coefficient and water content determination of almond leaves using beta radiation. Int. J. Innovative Sci. Eng. Tech. 3(3), 569–573 (2016)Google Scholar
  6. 6.
    Robert, B.R.: Methods for measuring water status and reducing transpirational water loss in trees. J. Arboric. 13, 56–61 (1987)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • I. A. Wagachchi
    • 1
  • B. B. D. S. Abeykoon
    • 1
  • R. D. K. Rassagala
    • 1
  • D. P. Jayathunga
    • 1
  • T. Kartheeswaran
    • 2
    Email author
  1. 1.Department of Computer Science and TechnologyUva Wellassa UniversityBadullaSri Lanka
  2. 2.Department of Physical ScienceVavuniya Campus of the University of JaffnaVavuniyaSri Lanka

Personalised recommendations