This paper describes a new machine vision system and Artificial Neural Networks based system for quality assessment of apple in real time, attending to external quality features of the fruits as size, color symmetry, weight and external defects. Based on external features, apple is correctly classified in this finding. The ANN model is developed using BP-ANN with a single hidden layer and sigmoid activation functions in MATLAB. The output variable is the quality of the apple. The modeling results showed that there was an excellent agreement between the experimental data and predicted values, with very good performance, fewer parameters and shorter calculation time. The model might be an alternative method for quality assessment of apple and provide consumers with a safer food supply.

Machine Vision; Real-Time Fruit Quality; Scaled Conjugate Gradient; Multilayer Perceptron; Back-Propagation Artificial Neural Network; Mean Square Error

[1] Tao, Y.; Morrow, C.T.; Heinemann, P.H.; Sommer, J.H.; “Automated machine vision inspection of potatoes”. ASAE Paper No. 90-3531, St. Joseph, MI, 1990.
[2] Zulhadi Zakaria, Nor Ashidi Mat Isa and Shahrel A. Suandi, “A Study on Neural Network Training Algorithm for Multiface Detection in Static Images”, World Academy of Science, Engineering and Technology 62-66, 2010.
[3] Okamura, N.K.; Delwiche, M.J.; Thompson, J.F.; “Raising grading by machine vision”. ASAE Paper No. 91-7011. St. Joseph, MI, 1991.
[4] Sarkar, N.; Wolfe, R.R.; “Feature extraction techniques for sorting tomatoes by computer vision”. TASAE Vol. 28(3): 970-974, 1985.
[5] Guyer, D.E.; Miles, G.E.; Gaultney, L.D.; Schereiber, M.M.; “Application of machine vision to shape analysis in leaf and plant identification”. 1993. TASAE Vol. 36(1): 163-171, 1993.
[6] Dickson, M.A.; Bausch, W.C.; Howarth, M.S.; “Classification of a broadleaf weed, a grassy weed, and corn using image processing techniques”. SPIE Vol. 2345: 297-305, 1994.
[7] Ruiz, L.A.; Moltó, E.; Juste, F.; Aleixos, N.; “Aplicación de métodos ópticos para la inspección automática de productos hortofrutícolas”. VI Congreso de la Sociedad Española de Ciencias Hortícolas, 25-28 de Abril de, Barcelona, 1995.
[8] YudongZhanga, ShuihuaWanga, Genlin Jib, PreethaPhillipsc,
“Fruit classification using computer vision and feedforward neural network”, Journal of Food Engineering, pp 167–177, 2014.
[9] Growe, T.G.; Delwiche, M.J.; “A system for fruit defect detection in real-time”. AGENG 96, Paper No. 96F-023, 1996.
[10]Ashutosh Kumar Bhatt, Durgesh Pant and Richa Singh, AI &
SOCIETY, Knowledge Culture and Communication, An analysis of the performance of Artificial Neural Network technique for apple classification, ISSN 0951-5666, AI & Soc DOI 10.1007/s00146-012-0425-z Volume 24, Number 1 August 2009.
[11]Moltó, E.; Aleixos, N.; Ruiz, L.A.; Vázquez, J.; Juste, F.; “An artificial vision system for fruit quality assessment”. AGENG 96, Madrid, Paper No. 96F-078, 1996.
[12]McCulloch, W., and W. Pitts , “A Logical Calculus of the Ideas Immanent in Nervous Activity”, Bulletin of Mathematical Biophysics, Vol. 5, pp.115–133. 1996.
[13]Zweiri, Y.H., Whidborne, J.F. and Sceviratne, L.D. A Three-term Backpropagation Algorithm. Neurocomputing. 50: 305-318, 2002.
[14]C.M. Bishop. Neural Networks for Pattern Recognition. Oxford University Press.Chapter 7, pp.253-294. 1995.
[15]A.K. Bhatt & D Pant, AI & SOCIETY, Knowledge Culture and Communication, Automatic apple grading model development based on back propagation neural network and machine vision, and its performance evaluation, ISSN 0951-5666, AI & Soc DOI 10.1007/s00146-012-0425-z Volume 30, Number 1 Feb, pp 45-56, 2015.
[16]Praveen Tripathi et. al., “ Efficiency Comparisons of Various Ann-Based and Svm-Based Techniques for Classification Problems: A Review”, International Journal of Scientific & Engineering Research Volume 8, Issue 10, October 2017, ISSN 2229-5518 pp 90-95, 2017.