Skip to main navigation menu Skip to main content Skip to site footer
ASPHC Baner

Vol. 23 No. 2 (2024)

Articles

A comparative study of distinguishing apple cultivars and a clone based on features of selected fruit parts and leaves using image processing and artificial intelligence

DOI: https://doi.org/10.24326/asphc.2024.5335
Submitted: 1 February 2024
Published: 30.04.2024

Abstract

This study aimed to identify the most useful white-fleshed apple samples to distinguish apple cultivars and a clone. Whole apples, apple slices, seeds, and leaves belonging to ‘Free Redstar’, clone 118, ‘Ligolina’, ‘Pink Braeburn’, and ‘Pinokio’ were imaged using a digital camera. The texture parameters were extracted from images in color channels L, a, b, R, G, B, X, Y, Z, U, V, and S. The classification models were built using traditional machine learning algorithms. Models developed using selected image seed textures allowed the classification of apple cultivars and a clone with the highest average accuracy of up to 97.4%. The apple seeds ‘Free Redstar’ were distinguished with the highest accuracy, equal to 100%. Machine learning models built based on the textures of apple skin allowed for the clone and cultivar classification with slightly lower correctness, reaching 94%. Meanwhile, the average accuracies for models involving selected flesh and leave textures reached 86.4% and 88.8%, respectively. All the most efficient models for classifying individual apple fruit parts and leaves were developed using Multilayer Perceptron. However, models combining selected image textures of apple skin, slices (flesh), seeds, and leaves produced the highest average accuracy of up to 99.6% in the case of Bayes Net. Thus, it was found that including features of different parts of apple fruit and apple leaves in one model can allow for the correct distinguishing of apples in terms of cultivar and clone.

References

  1. Azgomi, H., Haredasht, F.R., Motlagh, M.R.S. (2023). Diagnosis of some apple fruit diseases by using image processing and artificial neural network. Food Cont., 145, 109484. https://doi.org/10.1016/j.foodcont.2022.109484 DOI: https://doi.org/10.1016/j.foodcont.2022.109484
  2. Bhargava, A., Bansal, A. (2021). Classification and grading of multiple varieties of apple fruit. Food Anal. Methods, 14, 1359–1368. https://doi.org/10.1007/s12161-021-01970-0 DOI: https://doi.org/10.1007/s12161-021-01970-0
  3. Bouckaert, R.R., Frank, E., Hall, M., Kirkby, R., Reutemann, P., Seewald, A., Scuse, D. (2016). WEKA manual for version 3-9-1. University of Waikato, Hamilton, New Zealand.
  4. Buyukarikan, B., Ulker, E. (2022). Classification of physiological disorders in apples fruit using a hybrid model based on convolutional neural network and machine learning methods. Neural Comp. Appl., 34, 16973–16988. https://doi.org/10.1007/s00521-022-07350-x DOI: https://doi.org/10.1007/s00521-022-07350-x
  5. Chao, X., Sun, G., Zhao, H., Li, M., He, D. (2020). Identification of apple tree leaf diseases based on deep learning models. Symmetry, 12, 1065. https://doi.org/10.3390/sym12071065 DOI: https://doi.org/10.3390/sym12071065
  6. Chen, J., Han, J., Liu, C., Wang, Y., Shen, H., Li, L. (2022). A deep-learning method for the classification of apple varieties via leaf images from different growth periods in natural environment. Symmetry, 14, 1671. https://doi.org/10.3390/sym14081671 DOI: https://doi.org/10.3390/sym14081671
  7. da Silva, L.C., Souza, M.C., Sumere, B.R., Silva, L.G.S., da Cunha, D.T., Barbero, G.F., Bezerra, R.M.N., Rostagno, M.A. (2020). Simultaneous extraction and separation of bioactive compounds from apple pomace using pressurized liquids coupled on-line with solid-phase extraction. Food Chem., 318, 126450. https://doi.org/10.1016/j.foodchem.2020.126450 DOI: https://doi.org/10.1016/j.foodchem.2020.126450
  8. Ding, R., Qiao, Y., Yang, X., Jiang, H., Zhang, Y., Huang, Z., Wang, D., Liu, H. (2022). Improved Res-Net based apple leaf diseases identification. IFAC-Pap., 55, 78–82. https://doi.org/10.1016/j.ifacol.2022.11.118 DOI: https://doi.org/10.1016/j.ifacol.2022.11.118
  9. Dubey, S.R., Jalal, A.S. (2016). Apple disease classification using color, texture and shape features from images. Sig. Image Vid. Proc., 10, 819–826. https://doi.org/10.1007/s11760-015-0821-1 DOI: https://doi.org/10.1007/s11760-015-0821-1
  10. Fathizadeh, Z., Aboonajmi, M., Hassan-Beygi, S.R. (2021). Classification of apples based on the shelf life using ANN and data fusion. Food Anal. Methods, 14, 706–718. https://doi.org/10.1007/s12161-020-01913-1 DOI: https://doi.org/10.1007/s12161-020-01913-1
  11. Frank, E., Hall, M.A., Witten, I.H. (2016). The WEKA Workbench. Online Appendix for Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, Burlington.
  12. Krug, S., Hutschenreuther, T. (2023).. A case study toward apple cultivar classification using deep learning. AgriEngineering, 5, 814–828. https://doi.org/10.3390/agriengineering5020050 DOI: https://doi.org/10.3390/agriengineering5020050
  13. Liu, C., Han, J., Chen, B., Mao, J., Xue, Z., Li, S. (2020).. A novel identification method for apple (Malus domestica Borkh.) cultivars based on a deep convolutional neural network with leaf image input. Symmetry, 12, 217. https://doi.org/10.3390/sym12020217 DOI: https://doi.org/10.3390/sym12020217
  14. Matysiak, B., Ropelewska, E., Wrzodak, A., Kowalski, A., Kaniszewski, S. (2022). Yield and quality of romaine lettuce at different daily light integral in an indoor controlled environment. Agronomy, 12, 1026. https://doi.org/10.3390/agronomy12051026 DOI: https://doi.org/10.3390/agronomy12051026
  15. Nezbedova, L., McGhie, T., Christensen, M., Heyes, J., Nasef, N.A., Mehta, S. (2021). Onco-preventive and chemo-protective effects of apple bioactive compounds. Nutrients, 13, 4025. https://doi.org/10.3390/nu13114025 DOI: https://doi.org/10.3390/nu13114025
  16. Park, K., ki Hong, Y., hwan Kim, G., Lee, J. (2018). Classification of apple leaf conditions in hyperspectral images for diagnosis of Marssonina blotch using MRMR and deep neural network. Comput. Electron. Agric., 148, 179–187. https://doi.org/10.1016/j.compag.2018.02.025 DOI: https://doi.org/10.1016/j.compag.2018.02.025
  17. Rasool, A., Bhat, K.M., Mir, M.A., Jan, A., Dar, N.A., Mansoor, S. (2022). Elucidating genetic variability pertaining to flowering, maturity and morphological characters among various apple (Malus × domestica Borkh.) cultivars. South Afr. J. Bot., 145, 386–396. https://doi.org/10.1016/j.sajb.2021.06.010 DOI: https://doi.org/10.1016/j.sajb.2021.06.010
  18. Ronald, M., Evans, M. (2016). Classification of selected apple fruit varieties using Naive Bayes. Ind. J. Comput. Sci. Eng. (IJCSE), 7, 13–19.
  19. Ropelewska, E. (2020). The use of seed texture features for discriminating different cultivars of stored apples. J. Stored Prod. Res., 88, 101668. https://doi.org/10.1016/j.jspr.2020.101668 DOI: https://doi.org/10.1016/j.jspr.2020.101668
  20. Ropelewska, E. (2021). The application of image processing for cultivar discrimination of apples based on texture features of the skin, longitudinal section and cross-section. Eur. Food Res. Technol., 247, 1319–1331. https://doi.org/10.1007/s00217-021-03711-3 DOI: https://doi.org/10.1007/s00217-021-03711-3
  21. Ropelewska, E., Rutkowski, K.P. (2021). Cultivar discrimination of stored apple seeds based on geometric features determined using image analysis. J. Stored Prod. Res., 92, 101804. https://doi.org/10.1016/j.jspr.2021.101804 DOI: https://doi.org/10.1016/j.jspr.2021.101804
  22. Ropelewska, E., Szwejda‐Grzybowska, J. (2021). A comparative analysis of the discrimination of pepper (Capsicum annuum L.) based on the cross‐section and seed textures determined using image processing. J. Food Proc. Engineer., 44(6), e13694. https://doi.org/10.1111/jfpe.13694 DOI: https://doi.org/10.1111/jfpe.13694
  23. Ropelewska, E. (2022). Distinguishing lacto-fermented and fresh carrot slice images using the Multilayer Perceptron neural network and other machine learning algorithms from the groups of Functions, Meta, Trees, Lazy, Bayes and Rules. Eur. Food Res. Technol., 248, 2421–2429. https://doi.org/10.1007/s00217-022-04057-0 DOI: https://doi.org/10.1007/s00217-022-04057-0
  24. Ropelewska, E., Rady, A.M., Watson, N.J. (2023). Apricot stone classification using image analysis and machine learning. Sustainability, 15, 9259. https://doi.org/10.3390/su15129259 DOI: https://doi.org/10.3390/su15129259
  25. Sabanci, K., Ünlerşen, M.F. (2016). Different apple varieties classification using KNN and MLP algorithms. Int. J. Intell. Syst. Appl. Eng., 8, 17–20. DOI: https://doi.org/10.18201/ijisae.2016SpecialIssue-146967
  26. Shafi, W., Mansoor, S., Jan, S., Singh, D.B., Kazi, M., Raish, M., Alwadei, M., Mir, J.I., Ahmad, P. (2019). Variability in catechin and rutin contents and their antioxidant potential in diverse apple genotypes. Molecules, 24, 943. https://doi.org/10.3390/molecules24050943 DOI: https://doi.org/10.3390/molecules24050943
  27. Strzelecki, M., Szczypinski, P., Materka, A., Klepaczko, A. (2013). A software tool for automatic classification and segmentation of 2D/3D medical images. Nucl. Instrum. Methods Phys. Res., sec. A, Accel. Spectrom. Detect. Assoc. Equip., 702, 137–140. https://doi.org/10.1016/j.nima.2012.09.006 DOI: https://doi.org/10.1016/j.nima.2012.09.006
  28. Szczypinski, P.M., Strzelecki, M., Materka, A. (2007). Mazda-a software for texture analysis. In: Proceedings of the 2007 International Symposium on Information Technology Convergence (ISITC 2007), Jeonju, Korea, 23–24 November 2007, pp. 245–249. DOI: https://doi.org/10.1109/ISITC.2007.15
  29. Szczypinski, P.M., Strzelecki, M., Materka, A., Klepaczko, A. (2009). MaZda – A software package for image texture analysis. Comp. Meth. Prog. Biomed., 94, 66–76. https://doi.org/10.1016/j.cmpb.2008.08.005 DOI: https://doi.org/10.1016/j.cmpb.2008.08.005
  30. Taner, A., Mengstu, M.T., Selvi, K.Ç., Duran, H., Kabaş, Ö., Gür, İ., Karaköse, T., Gheorghiță, N.-E. (2023). Multiclass apple varieties classification using machine learning with histogram of oriented gradient and color moments. Appl. Sci., 13, 7682. https://doi.org/10.3390/app13137682 DOI: https://doi.org/10.3390/app13137682
  31. Witten, I.H., Frank, E. (2005). Data mining: practical machine learning tools and techniques. Elsevier, San Francisco.
  32. Wu, J., Gao, H., Zhao, L., Liao, X., Chen, F., Wang, Z., Hu, X. (2007). Chemical compositional characterization of some apple cultivars. Food Chem., 103, 88–93. https://doi.org/10.1016/j.foodchem.2006.07.030 DOI: https://doi.org/10.1016/j.foodchem.2006.07.030
  33. Zhang, S., Wang, D., Yu, C. (2023). Apple leaf disease recognition method based on Siamese dilated Inception network with less training samples. Comp. Electron. Agric., 213, 108188. https://doi.org/10.1016/j.compag.2023.108188 DOI: https://doi.org/10.1016/j.compag.2023.108188
  34. Zhang, M., Yin, Y., Li, Y., Jiang, Y., Hu, X., Yi, J. (2023). Chemometric classification of apple cultivars based on physicochemical properties: raw material selection for processing applications. Foods, 12, 3095. https://doi.org/10.3390/foods12163095 DOI: https://doi.org/10.3390/foods12163095
  35. Żurawicz, E., Zagaja, S.W. (1999). Breeding apple cultivars at the Research Institute of Pomology and Floriculture, Skierniewice, Poland. Acta Hort., 484, 221–224. https://doi.org/10.17660/ActaHortic.1998.484.38 DOI: https://doi.org/10.17660/ActaHortic.1998.484.38

Downloads

Download data is not yet available.

Similar Articles

<< < 42 43 44 45 46 47 48 49 50 51 > >> 

You may also start an advanced similarity search for this article.