Classification of Date Fruit Types Using CNN Algorithm Based on Type

Abstract

Date fruits are an important commodity in the agriculture and food industry. However, in the process of sales and distribution to ordinary people, there are often errors in identifying different types of date fruits. Therefore, this research aims to develop an automatic classification system to distinguish the types of date fruits based on their types using the Convolutional Neural Network (CNN) algorithm. The case study was conducted at Hamima Dates date shop. The data used are fruit images with 9 categories and a total of 1658 samples, which are divided into 1496 samples for training data and 162 samples for testing data. The test results show that the CNN algorithm has a high level of accuracy in classifying the type of date fruit, with an accuracy of 96%. In this study, feature analysis was also conducted to determine the contribution of each feature to the classification of date fruit types. The results of this study can be the basis for the development of a more sophisticated date fruit automatic classification system and can be applied to other types of fruits