Estimation of biochemical characteristics of blood orange (Citrus sinensis cv. Moro) using machine vision and ANNs

Authors
Mahdih Bashkar 1
Majid Dowlati 2
Iman Golpour 3
Hossein Meighani 4
1 Department of Mechanical Engineering of Biosystems, Faculty of Agriculture, University of Jiroft, Jiroft, Iran.
2 Department of Food Science and Technology, Tuyserkan Faculty of Engineering and Natural Resources, Bu-Ali Sina University, Hamedan, Iran.
3 Department of Mechanical Engineering of Biosystems, Faculty of Agriculture, University of Urmia, Urmia, Iran.
4 Department of Horticultural Engineering, Faculty of Agriculture, University of Jiroft, Jiroft, Iran.
10.22034/FSCT.19.125.157
Abstract
Nowadays, citrus fruits, especially oranges, is very important in the human nutrition regime, and its quality characteristics assessment is very important. This study aimed to predict some biochemical characteristics of blood orange, using machine vision and artificial neural networks. In this experiment, the amount of vitamin C content, sugar content, and acidity (pH) were obtained using destructive laboratory methods. Images of blood orange samples were captured and 108 texture features and 57 color features were extracted on CIElab, RGB, HSV, and HIS color spaces and finally, the artificial neural networks method has been used to estimate the desired properties. To evaluate and select the most optimal artificial neural network, a feed-forward neural networks with Levenberg-Marquardt learning algorithm, the different number of neurons, and different transfer functions in the hidden and output layers was used. Finally, using the best neural network and 165 textural-color features, the amount of vitamin C content, sugar content, and pH were estimated with a correlation coefficient of 0.950, 0.968, and 0.884, respectively. Therefore, considering the appropriate correlation coefficient, machine vision and image processing technology can estimate some biochemical characteristics of blood oranges accurately.
Keywords
Biochemical Characteristics
Blood orange
Color and Texture
Image processing
ANNs

Subjects

[1] Fotouhi Ghazvini, R. & Fattahi Moghadam, J. (2006). Citrus Growing in Iran. (2th ed.), Guilan University Press, 305p.
[2] FAO. (2011). Citrus fruit – fresh and processed, annual statistics, 2009. Commodities and Trade Division, FAO.
[3] Anonymous (2019) Statistical book of Agricultural of Iran. Iranian Statistical Centre, Tehran.
[4] Adelkhani, A., Beheshti, B., Minaei, S. & Javadikia, H. )2016(. Taste determination of Thompson orange using image processing based on ANFIS and ANN-GA methods. Journal of Food Science and Technology, 13(56), 45-55. (In Farsi)
[5] Majumdar, S. & Jayas, D.S. (2000). Classification of cereal grains using machine vision. I. Morphology models. Transactions of the ASAE, 43(6), 1669-1675.
[6] Dowlati, M., Mohtasebi, S. S. & M. de-la Guardia, M. (2012). Application of machine-vision techniques to fish-quality assessment. TRAC- Trends in Analytical Chemistry, 40, 168-179.
[7] Dowlati, M., Mohtasebi, S. S., Omid, M., Razavi, S. H., Jamzad, M. & De La Guardia, M. (2013). Freshness assessment of gilthead sea bream (Sparus aurata) by machine vision based on gill and eye color changes. Journal of Food Engineering. 119(2), 277-287.
[8] Butz, P., Hofmann, C. & Tauscher, B. (2005). Recent developments in non-invasive techniques for fresh fruit and vegetable internal quality analysis. Journal of Food Science, 70, 131–134.
[9] Multag, W.K., Ali, S.K., Aydam, Z.M. & Taher, B. H. (2020). Feature extraction methods: a review. Journal of Physics: Conference Series, 1591: 012028.
[10] Zare-Chahoki, M.A. (2011) Methods of Multivariate Analysis with SPSS. Publications of Faculty of Natural Resources, Tehran University, Tehran.
[11] Al-Saif, A.M., Abdel-Sattar, M., Aboukarima, A.M. & Eshra, D.H. (2021). Application of a multilayer perceptron artificial neural network for identification of peach cultivars based on physical characteristics. PeerJ, DOI 10.7717/peerj.11529.
[12] Li, Y., Feng, X., Liu, Y. & Han, X. (2021). Apple quality identification and classification by image processing based on convolutional neural networks. Scientific Reports, 11(1): 1-15.
[13] Kondo, N., Ahmad, U., Monta, M. & Murase, H. (2000). Machine vision based quality evaluation of Iyocan orange fruit using neural network. Computers and Electronics in Agriculture, 29, 135-147.
[14] Mendoza, F. & Aguilera, J.M. (2004). Application of image analysis for classification of ripening bananas. Journal of Food Science, 69, 471-477.
[15] Kavdir, I. & Guyer, D.E. (2002). Apple sorting using Artificial Neural Network and Special imaging. Trans. ASAE, 45, 1995–2005.
[16] Jafari, A., Fazayeli, A. & Zarezadeh, M.R. (2014). Estimation of orange skin thickness based on visual texture coarseness. Biosystems Engineering, 117, 73-82.
[17] Masoudi; H. & Rohani, A. (2017). Mass and volume prediction of orange fruit (Dezful Local Variety) using MLP neural networks. Journal of Agricultural Engineering, 39(2), 133-142.
[18] Neelamma, K.P., Virendra, S.M. & Ravi, M.Y. (2011). Color and texture based identification and classification of food Grains using different Color Models and Haralick features. International Journal on Computer Science and Engineering, 12(3), 3669-3680.
[19] Zhang, M.S., Ustin, L., Rejmankova, E. & Sanderson, E.W. (1997). Monitoring pacific coast salt marshes using remote sensing. Ecological Applications, 73, 1039-1053.
[20] Hunt, R.W.G. (1991). Measuring color (2th ed.), New York: Ellis Horwood.
[21] Golpour, I., Amiri Parian, J., Amiri Chayjan, R. & Khazaei, J. (2015). Recognition of paddy, brown rice and white rice cultivars based on textural features of images and artificial neural network. Journal of Agricultural Machinery, 5(1), 73-81.
[22] AOAC. (1995). Official method of analysis of AOAC international, 16th edition. The United States of America, DC.
[23] Roe, J.H. (1955). The determination of sugar in blood and spinal fluid with anthrone reagent. Journal of Biological Chemistry, 212, 335-343.
[24] Momenzadeh, L., Zomorodian, A. & Mowla, A. (2012). Applying artificial neural network for drying time prediction of green pea in a microwave assisted fluidized bed dryer. Journal of Agricultural Science and Technology, 14: 513-522
[25] Hernandez-Perez, J.A., Garcıa-Alvarado, M.A., Trystram, G. & Heyd, B. (2004). Neural networks for the heat and mass transfer prediction during drying of cassava and mango. Innovative Food Science and Emerging Technologies, 5, 57–64.
[26] Erenturk, S. & Erenturk, S. (2007). Comparison of genetic algorithm and neural network approaches for the drying process of carrot. Journal of Food Engineering, 78, 905-1884.
[27] Khoshtaghaza, M.H., Amiri-Chayjan, R., Montazer, G.H. & Minaei, S. (2007) Production of head rice yield in fixed bed drying using artificial neural network. Journal of Agricultural Engineering Research, 8(2), 135-156. (In Farsi)