Fruit classification is essential in various industrial settings, such as factories, supermarkets, and other places. Fruit classification may also be beneficial to persons with unique nutritional needs who utilize it to choose the proper fruits. Manual sorting was formerly used for fruit classification is time-consuming and requires continual human presence. Many fruit classification machine learning techniques have been proposed in the past. Deep learning may be a powerful engine for generating actionable results in today's reality because of its detection and classification abilities. As a result, a convolutional neural network was employed to construct an effective fruit classification model. It makes use of the fruits 360 dataset, which contains 131 different fruit and vegetable varieties. In this paper, we used three fruits, divided into three categories: good, raw, and damaged. The model was made in Keras. It had been trained for 50 epochs and had a 95% accuracy rate. © 2021 IEEE.