The current research on automatic recognition of vegetable and fruit images is more focused on a single fruit and vegetable image without background environment, and more features such as texture and color are extracted, and shallow learning technology is used to realize the recognition of vegetable and fruit images. The method cannot meet the classification and identification of various fruits and vegetables. The main purpose of this paper is to carry out research on fruit and vegetable identification and nutritional analysis based on the knowledge of multilayer perceptron and neural network (NN). In view of the above background, this research focuses on the research on IR of fruits and vegetables, using deep learning methods to improve the recognition rate of fruits and vegetables images, and constructing models through CNNs to achieve classification and recognition. Experiments show that the number of network layers has a greater impact on IR, and the deeper the network depth, the higher the IR rate. Considering that the increase in the number of network layers will affect the structural complexity of the network model and increase the amount of mathematical operations, reasonable network layer selection is particularly important in IR.

Aditya Ijaz. Fruit and Vegetable Recognition and Nutrition Analysis Based on Multilayer Perceptron and Neural Network. International Journal of Neural Network (2020), Vol. 1, Issue 4: 42-51. https://doi.org/10.38007/NN.2020.010406.

[1] Zouhri A, Amakdouf H, Mallahi M E, et al. Invariant Gaussian–Hermite Moments Based NNs for 3D Object Classification. Pattern Recognition and Image Analysis. (2020) 30(1):87-96. https://doi.org/10.1134/S1054661820010186

[2] Chishti M A, Al S. Assessing the Efficacy of Logistic Regression, Multilayer Perceptron, and CNN for Handwritten Digit Recognition. IJCDS Journal. (2020) 9(2):299-308. https://doi.org/10.12785/ijcds/090215

[3] Karaki Y, Ivanov N. Hyperparameters of Multilayer Perceptron with Normal Distributed Weights. Pattern Recognition and Image Analysis. (2020) 30(2):170-173. https://doi.org/10.1134/S1054661820020054

[4] Panghal S, Kumar M. A Multilayer Perceptron NN Approach for the Solution of Hyperbolic Telegraph Equations. Network: Computation in Neural Systems. (2020) 32(2-4):65-82. https://doi.org/10.1080/0954898X.2020.2015005

[5] Moshkbar B K. Bayesian Regularization of Multilayer Perceptron NN for Estimation of Mass Attenuation Coefficient of Gamma Radiation In Comparison with Different Supervised Model-Free Methods. Journal of Instrumentation. (2020) 15(11):P11019-P11019. https://doi.org/10.1088/1748-0221/15/11/P11019

[6] Balamurugan M. Multilayer Perceptron NN Analysis: Prediction of School Outcome from the Dimensions of School Process. Xi'an Jianzhu Keji Daxue Xuebao/Journal of Xi'an University of Architecture & Technology. (2020) XIII(7):59-67.

[7] Raziani S, Ahmadian S, Jalali S, et al. An Efficient Hybrid Model Based on Modified Whale Optimization Algorithm and Multilayer Perceptron NN for Medical Classification Problems. Journal of Bionic Engineering. (2020) 19(5):1504-1521. https://doi.org/10.1007/s42235-022-00216-x

[8] Verma P, Awasthi V K, Sahu S K. Classification of Coronary Artery Disease Using Multilayer Perceptron NN. International Journal of Applied Evolutionary Computation. (2020) 12(3):35-43. https://doi.org/10.4018/IJAEC.2020070103

[9] Zvarevashe K, Olugbara O O. Recognition of Speech Emotion Using Custom 2D-Convolution NN Deep Learning Algorithm. Intelligent Data Analysis. (2020) 24(5):1065-1086. https://doi.org/10.3233/IDA-194747

[10] Otoom A F. Software Effort Classification with Multilayer Perceptron NNs. International Journal of Advanced Trends in Computer Science and Engineering. (2020) 9(2):1678-1689. https://doi.org/10.30534/ijatcse/2020/119922020

[11] Vladimir G, Yury M, Natalya K. Pattern Recognition Techniques for Classifying Aeroballistic Flying Vehicle Paths. Neural Computing and Applications. (2020) 34(5):4033-4045. https://doi.org/10.1007/s00521-021-06662-8

[12] Asadi N, Scott K A, Komarov A S, et al. Evaluation of a NN With Uncertainty for Detection of Ice and Water in SAR Imagery. IEEE Transactions on Geoscience and Remote Sensing. (2020) (99):1-13. https://doi.org/10.1109/TGRS.2020.2992454

[13] Saha S, Dawson J, Murimi M, et al. Effects of a Nutrition Education Intervention on Fruit and Vegetable Consumption-Related Dietary Behavioural Factors among Elementary School Children: Health Education Journal. (2020) 79(8):963-973. https://doi.org/10.1177/0017896920944421

[14] Kojima G, Taniguchi Y, Urano T. Fruit and Vegetable Consumption and Incident Frailty in Older Adults: A Systematic Review and Meta-Analysis. The Journal of Frailty & Aging. (2020) 11(1):45-50. https://doi.org/10.14283/jfa.2020.32

[15] Aune D, Halvorsen R E, Molin M. Fruit and Vegetable Consumption and the Risk of Type 2 Diabetes: A Systematic Review and Dose–Response Meta-Analysis of Prospective Studies. BMJ Nutrition, Prevention and Health. (2020) 4(2):519-531. https://doi.org/10.1136/bmjnph-2020-000218

[16] Dumas B, Lee S H, Park S, et al. Associations Between Perceived Fruit and Vegetable Intake and Nutrition Messaging: Results from a Population-Based Survey Among US Adults. Current Developments in Nutrition. (2020) 4(Supplement_2):1364-1364. https://doi.org/10.1093/cdn/nzaa060_002

[17] Alnaim L, Taylor M, Gibbs H, et al. A Pilot Nutrition and Cooking Skills Program Improves Fruit Intake, Nutrition Knowledge, and Attitudes Toward Fruit and Vegetable. Current Developments in Nutrition. (2020) 5(Supplement_2):957-957. https://doi.org/10.1093/cdn/nzab051_001

[18] Azekour K, Bidi A, Bouhali E. Socioeconomic Characteristics and Fruit/Vegetable Intakes among Scholar Children in the Oasis of Tafilalet, Southeastern Morocco. Nutricion Clinica y Dietetica Hospitalaria. (2020) 39(3):24-28.