\`x^2+y_1+z_12^34\`
Advanced Search
Article Contents
Article Contents

Neural network training in SCILAB for classifying mango (Mangifera indica) according to maturity level using the RGB color model

Academic Editor: Med Amine Laribi

Abstract Full Text(HTML) Figure(16) Related Papers Cited by
  • Industries that use fruits as raw materials must, at some point in the process, classify them to discard the unsuitable ones and thus ensure the quality of the final product. To produce mango nectar, it is necessary to ensure that the mango is mature enough to start the extraction of the nectar; however, sorting thousands of mangoes may require many people, who can easily lose attention and reduce the accuracy of the result. Such kind of decision can be supported by current Artificial Intelligence techniques. The theoretical details of the processing are presented, as well as the programming code of the neural network using SCILAB as a computer language; the code includes the color extraction from mango images. SCILAB programming is simple, efficient and does not require computers with large processing capacity. The classification was validated with 30 images (TIF format) of Manila variety mango; the mangoes were placed on a blue background to easily separate the background from the object of interest. Four and six mangoes were used to train the neural network. This application of neural networks is part of an undergraduate course on artificial intelligence, which shows the potential of these techniques for solving real and concrete problems.

    Mathematics Subject Classification: Article.

    Citation:

    \begin{equation} \\ \end{equation}
  • 加载中
  • Figure 1.  Manual mango classification [2].

    Figure 2.  Stages for the implementation of an AI computer program.

    Figure 3.  Levels of mango maturity.

    Figure 4.  Segmentation applied to separate the airplane from the sky (including clouds).

    Figure 5.  Some colors and the corresponding RGB values.

    Figure 6.  a), b), c), d) Color extraction images, e) SCILAB code.

    Figure 7.  Model of an artificial neuron, named perceptron, with 3 input variables.

    Figure 8.  An ANN with 3 layers.

    Figure 9.  SCILAB code to calculate de ANN output.

    Figure 10.  Training of an ANN from known values of $ X $ and $ Y $ vectors.

    Figure 11.  SCILAB program for ANN training.

    Figure 12.  Mangoes selected for ANN training.

    Figure 13.  Input and output variables for ANN training.

    Figure 14.  Preliminary result of the classification of 30 mangoes.

    Figure 15.  Green, medium, and mature mangoes for ANN training.

    Figure 16.  Result with improved training using 6 mangoes.

  • [1] S.N. JhaS. Chopra and A.R.P. Kingsly, Modeling of color values for nondestructive evaluation of maturity of mango, Journal of Food Engineering, 78 (2007), 22-26. 
    [2] In: https://www.magmar.com.mx/, available 4th July 2021.
    [3] S.J. Russell and  P. NorvigArtificial Intelligence: A modern Approach, Prentice Hall, New Jersey, USA, 1995. 
    [4] Bughin, J., Seong, J., Manyika, J., Chui, M. and Joshi, R., Notes from AI frontier: Modeling the impact of AI on the world economy. Discussion paper, 2018, McKinsey Global Institute.
    [5] S. Lucci and  D. KopecArtificial Intelligence in the 21st Century, Mercury Learning and Information, VA, USA, 2015. 
    [6] D.S. Prabha and J.S. Kumar, Assessment of banana fruit maturity by image processing technique, J Food Sci Technol, 52 (2015), 1216-1327. 
    [7] R. TorresE.J. MontesO.A. Pérez and R.D. Andrade, Relación del Color y del Estado de Madurez, con las Propiedades FisicoquȪmica de Frutas Tropicales, Información Tecnológica, 24 (2013), 51-56. 
    [8] J.C. RussThe Image Processing Handbook, Prentice Hall, 1999. 
    [9] R.C. González and  R.E. WoodsDigital Image Processing, Prentice Hall, 2002. 
    [10] F. Rosenblatt, The perceptron: A probabilistic model for information storage and organization in the brain, Psychological Review, 65 (1958). 
    [11] Rojas, R., The Backpropagation Algorithm. Neural Networks, 1996, pp. 149-182. Springer-Verlag.
    [12] D.P. Mandic, A generalized normalized gradient descent algorithm, IEEE Signal Processing Letters, 11 (2004), 115-118. 
  • 加载中
Open Access Under a Creative Commons license

Figures(16)

SHARE

Article Metrics

HTML views(1512) PDF downloads(335) Cited by(0)

Access History

Other Articles By Authors

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return