Date Fruit Classification Based on Surface Quality Using Convolutional Neural Network Models

Classifying the quality of dates after harvesting crop plays a significant role in reducing waste from date fruit production. About one million tons is produced annually Saudi Arabia. Part this production goes to local factories be and packaged ready for use. sorting edible inedible first most important stages process industry. As still performed manually Arabia, may cause an increase reduce efficiency Therefore, our paper, we propose system automate classification The proposed focuses on classifying at postharvesting stage. By automating stage, can efficiency, raise accuracy, control product quality, perform data analysis within result, increases market competitiveness, reduces costs, productivity. was developed based convolutional neural network models. For purpose training models, constructed new image dataset that contains two main classes have images with excellent surface another class poor quality. results show used model classify their accuracy 97%.