Tomato Fruit Detection Using Modified Yolov5m Model with Convolutional Neural Networks

Abstract

The farming industry is facing the major challenge of intensive and inefficient harvesting labors. Thus, an efficient and automated fruit harvesting system is required. In this study, three object classification models based on Yolov5m integrated with BoTNet, ShuffleNet, and GhostNet convolutional neural networks (CNNs), respectively, are proposed for the automatic detection of tomato fruit. The various models were trained using 1508 normalized images containing three classes of cherry tomatoes, namely ripe, immature, and damaged. The detection accuracy for the three classes was found to be 94%, 95%, and 96%, respectively, for the modified Yolov5m + BoTNet model. The model thus appeared to provide a promising basis for the further development of automated harvesting systems for tomato fruit.