Comparison between soft computing methods for tomato quality grading using machine vision

  • Mohammad Saber IrajiEmail author
Original Paper


The combination of machine vision and soft computing approaches in the agriculture industry, using training data and automation, can improve processing times by eliminating time consuming manual assessment. The tomato is one of the most popular and highest selling fruits in the world, and its quality is judged by its visual characteristics. Classification of tomatoes into quality grades is therefore very important. In this study, we proposed a series of methods for predicting tomato quality classes based on artificial intelligence. We implemented a multi-layer architecture of a SUB-adaptive neuro fuzzy inference system (MLA-ANFIS) approach using various combinations of multiple input features, neural networks, regression and extreme learning machines (ELMs) based on a tomato image data set with seven input features that were collected from a farm. A deep stacked sparse auto-encoders (DSSAEs) method was proposed for tomato quality grading using image data directly, instead of analysing features extracted from the tomato images. The DSSAEs method was more accurate than previous methods, and used different methodology to previously proposed approaches for the evaluation of the tomato quality grades. The proposed method achieved a sensitivity of 83.2%, specificity of 96.50% and g-mean of 89.40% with accuracy of 95.5%. It may thus be able to improve inspection and quality processing of tomatoes.


Deep stacked sparse auto-encoders Tomato quality Adaptive fuzzy neural network ELM Neural networks 



Funding was provided by Payame Noor University.

Compliance with ethical standards

Conflict of interest

No conflicts of interest are declared related to the publication of this paper.


  1. 1.
    G. Polder, G. van der Heijden, in Hyperspectral Imaging for Food Quality Analysis and Control, ed. by D.W. Sun Measuring ripening of tomatoes using imaging spectrometry (Academic Press, London, 2010), pp. 369–402Google Scholar
  2. 2.
    Y. Zhang et al., Fruit classification using computer vision and feedforward neural network. J. Food Eng. 143, 167–177 (2014)Google Scholar
  3. 3.
    I.R. Donis-González, D.E. Guyer, Classification of processing asparagus sections using color images. Comput. Electron. Agric. 127, 236–241 (2016)Google Scholar
  4. 4.
    G.L. Grinblat et al., Deep learning for plant identification using vein morphological patterns. Comput. Electron. Agric. 127, 418–424 (2016)Google Scholar
  5. 5.
    A. Wongsriworaphon, B. Arnonkijpanich, S. Pathumnakul, An approach based on digital image analysis to estimate the live weights of pigs in farm environments. Comput. Electron. Agric. 115, 26–33 (2015)Google Scholar
  6. 6.
    M.I. Chacon-Murguia, J.I. Nevarez-Santana, W.J. Perez-Regalado, Subjective measurement of cosmetic defects using a computational intelligence approach. Eng. Appl. Artif. Intell. 23(8), 1380–1387 (2010)Google Scholar
  7. 7.
    J.-D. Wu, C.-C. Hsu, G.-Z. Wu, Fault gear identification and classification using discrete wavelet transform and adaptive neuro-fuzzy inference. Expert. Syst. Appl. 36(3), 6244–6255 (2009)Google Scholar
  8. 8.
    C. Li et al., Soft measurement of wood defects based on LDA feature fusion and compressed sensor images. J. For. Res. 28(6), 1285–1292 (2017)Google Scholar
  9. 9.
    Z. Huang et al., Self-regulation in chemical and bio-engineering materials for intelligent systems. CAAI Trans. Intell. Technol. 3(1), 40–48 (2018)Google Scholar
  10. 10.
    B. Ye et al., Heritability of growth traits in the Asian seabass (Lates calcarifer). Aquac. Fish. 2(3), 112–118 (2017)Google Scholar
  11. 11.
    J. Beaty, Y. Chen, Can back-calculated lengths based on otoliths measurements provide reliable estimates of Atlantic halibut (Hippoglossus hippoglossus) growth in the Gulf of Maine (USA). Aquac. Fish. 2(1), 24–33 (2017)Google Scholar
  12. 12.
    M.A. Cliff et al., Effects of nutrient solution electrical conductivity on the compositional and sensory characteristics of greenhouse tomato fruit. Postharvest Biol. Technol. 74, 132–140 (2012)Google Scholar
  13. 13.
    M.A. Ashraf, N. Kondo, T. Shiigi, Use of machine vision to sort tomato seedlings for grafting robot. Eng. Agric. Environ. Food 4(4), 119–125 (2011)Google Scholar
  14. 14.
    K.C. Deegan et al., Application of a sorting procedure to greenhouse-grown cucumbers and tomatoes. LWT Food Sci. Technol. 43(3), 393–400 (2010)Google Scholar
  15. 15.
    B.-K. Cho et al., Detection of cuticle defects on cherry tomatoes using hyperspectral fluorescence imagery. Postharvest biology and technology 76, 40–49 (2013)Google Scholar
  16. 16.
    G. Moreda et al., Shape determination of horticultural produce using two-dimensional computer vision—a review. J. Food Eng. 108(2), 245–261 (2012)Google Scholar
  17. 17.
    N. Goel, P. Sehgal, Fuzzy classification of pre-harvest tomatoes for ripeness estimation—an approach based on automatic rule learning using decision tree. Appl. Soft Comput. 36, 45–56 (2015)Google Scholar
  18. 18.
    A. Rafiq, H.A. Makroo, M.K. Hazarika, Artificial neural network-based image analysis for evaluation of quality attributes of agricultural produce. J. Food Process. Preserv. 40(5), 1010–1019 (2016)Google Scholar
  19. 19.
    K. Mollazade et al., Analysis of texture-based features for predicting mechanical properties of horticultural products by laser light backscattering imaging. Comput. Electron. Agric. 98, 34–45 (2013)Google Scholar
  20. 20.
    A. Wang et al., A novel pattern recognition algorithm: combining ART network with SVM to reconstruct a multi-class classifier. Comput. Math. Appl. 57(11), 1908–1914 (2009)Google Scholar
  21. 21.
    H.M. Velioğlu, İH. Boyacı, Ş Kurultay, Determination of visual quality of tomato paste using computerized inspection system and artificial neural networks. Computers and electronics in agriculture 77(2), 147–154 (2011)Google Scholar
  22. 22.
    M. Zaborowicz et al., Application of neural image analysis in evaluating the quality of greenhouse tomatoes. Sci. Hortic. 218, 222–229 (2017)Google Scholar
  23. 23.
    A.M.C. Martinez, S.H. Mallidi, B.T. Meyer, On the relevance of auditory-based Gabor features for deep learning in robust speech recognition. Comput. Speech Lang. 45, 21–38 (2017)Google Scholar
  24. 24.
    K. Tian et al., Boosting compound-protein interaction prediction by deep learning. Methods 110, 64–72 (2016)Google Scholar
  25. 25.
    A. Singh, C.S. Tucker, A machine learning approach to product review disambiguation based on function, form and behavior classification. Decis. Support Syst. 97, 81–91 (2017)Google Scholar
  26. 26.
    K. Lu et al., Efficient deep network for vision-based object detection in robotic applications. Neurocomputing 245, 31–45 (2017)Google Scholar
  27. 27.
    K. Guo, S. Wu, Y. Xu, Face recognition using both visible light image and near-infrared image and a deep network. CAAI Trans. Intell. Technol. 2(1), 39–47 (2017)Google Scholar
  28. 28.
    N. Wahab, A. Khan, Y.S. Lee, Two-phase deep convolutional neural network for reducing class skewness in histopathological images based breast cancer detection. Comput. Biol. Med. 85, 86–97 (2017)PubMedGoogle Scholar
  29. 29.
    M. Brahimi, K. Boukhalfa, A. Moussaoui, Deep learning for tomato diseases: classification and symptoms visualization. Appl. Artif. Intell. 31(4), 1–17 (2017)Google Scholar
  30. 30.
    M.S. Iraji, A. Tosinia, Classification tomatoes on machine vision with fuzzy the mamdani inference, adaptive neuro fuzzy inference system based (Anfis-Sugeno). Aust. J. Basic Appl. Sci. 5(11), 846–853 (2011)Google Scholar
  31. 31.
    S. Geman, E. Bienenstock, R. Doursat, Neural networks and the bias/variance dilemma. Neural Comput. 4(1), 1–58 (2008)Google Scholar
  32. 32.
    K. Hornik, M. Stinchcombe, H. White, Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)Google Scholar
  33. 33.
    B.K. Vaughn, Data analysis using regression and multilevel/hierarchical models, by Gelman, A. & Hill, J. J. Educ. Meas. 45(1), 94–97 (2008)Google Scholar
  34. 34.
    G.-B. Huang, Q.-Y. Zhu, C.-K. Siew, Extreme learning machine: theory and applications. Neurocomputing 70(1), 489–501 (2006)Google Scholar
  35. 35.
    G. Feng et al., Error minimized extreme learning machine with growth of hidden nodes and incremental learning. IEEE Trans. Neural Netw. 20(8), 1352–1357 (2009)PubMedGoogle Scholar
  36. 36.
    G. Cosma et al., A survey on computational intelligence approaches for predictive modeling in prostate cancer. Expert. Syst. Appl. 70, 1–19 (2017)Google Scholar
  37. 37.
    Y. Zhang, E. Zhang, W. Chen, Deep neural network for halftone image classification based on sparse auto-encoder. Eng. Appl. Artif. Intell. 50, 245–255 (2016)Google Scholar
  38. 38.
    Y. Bengio, Learning deep architectures for AI. Found. Trends® Mach. Learn. 2(1), 1–127 (2009)Google Scholar
  39. 39.
    Z. Zhu et al., Deep learning representation using autoencoder for 3D shape retrieval. Neurocomputing 204, 41–50 (2016)Google Scholar
  40. 40.
    S.-Z. Su et al., Sparse auto-encoder based feature learning for human body detection in depth image. Signal Process 112, 43–52 (2015)Google Scholar
  41. 41.
    U. Çaydaş, A. Hasçalık, S. Ekici, An adaptive neuro-fuzzy inference system (ANFIS) model for wire-EDM. Expert. Syst. Appl. 36(3), 6135–6139 (2009)Google Scholar
  42. 42.
    Y.-M. Wang, T.M. Elhag, An adaptive neuro-fuzzy inference system for bridge risk assessment. Expert. Syst. Appl. 34(4), 3099–3106 (2008)Google Scholar
  43. 43.
    Y. Feng et al., Modeling reference evapotranspiration using extreme learning machine and generalized regression neural network only with temperature data. Comput. Electron. Agric. 136, 71–78 (2017)Google Scholar
  44. 44.
    J.-Z. Wang et al., Forecasting stock indices with back propagation neural network. Expert. Syst. Appl. 38(11), 14346–14355 (2011)Google Scholar
  45. 45.
    L.I. Kuncheva, Combining pattern classifiers: methods and algorithms (Wiley, New York, 2004)Google Scholar
  46. 46.
    M.S. Iraji, Multi-layer architecture for adaptive fuzzy inference system with a large number of input features. Cogn. Syst. Res. 42, 23–41 (2017)Google Scholar
  47. 47.
    G.-B. Huang, D.H. Wang, Y. Lan, Extreme learning machines: a survey. Int. J. Mach. Learn. Cybern. 2(2), 107–122 (2011)Google Scholar
  48. 48.
    G.-B. Huang et al., Extreme learning machine for regression and multiclass classification. IEEE Trans. Syst. Man Cybern Part B 42(2), 513–529 (2012)Google Scholar
  49. 49.
    F. Han, D.-S. Huang, Improved extreme learning machine for function approximation by encoding a priori information. Neurocomputing 69(16), 2369–2373 (2006)Google Scholar
  50. 50.
    J.V. Carter et al., ROC-ing along: evaluation and interpretation of receiver operating characteristic curves. Surgery 159(6), 1638–1645 (2016)PubMedGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer Engineering and Information TechnologyPayame Noor University (PNU)TehranIran

Personalised recommendations