期刊
PLANTS-BASEL
卷 12, 期 4, 页码 -出版社
MDPI
DOI: 10.3390/plants12040790
关键词
deep learning; convolution neural network; Yolov5; tomato fruit classification
In this study, four deep learning frameworks combining Yolov5m with ResNet50, ResNet-101, and EfficientNet-B0 were proposed for classifying tomato fruit on the vine into ripe, immature, and damaged categories. The prediction accuracy for ripe and immature tomatoes was found to be 100% when combining Yolov5m with ResNet-101, while the accuracy for damaged tomatoes was 94% using Yolov5m with the Efficient-B0 model. The testing accuracies of ResNet-50, EfficientNet-B0, Yolov5m, and ResNet-101 networks were 98%, 98%, 97%, and 97% respectively. Thus, all four frameworks have the potential for automated tomato fruit classification in agriculture.
Four deep learning frameworks consisting of Yolov5m and Yolov5m combined with ResNet50, ResNet-101, and EfficientNet-B0, respectively, are proposed for classifying tomato fruit on the vine into three categories: ripe, immature, and damaged. For a training dataset consisting of 4500 images and a training process with 200 epochs, a batch size of 128, and an image size of 224 x 224 pixels, the prediction accuracy for ripe and immature tomatoes is found to be 100% when combining Yolo5m with ResNet-101. Meanwhile, the prediction accuracy for damaged tomatoes is 94% when using Yolo5m with the Efficient-B0 model. The ResNet-50, EfficientNet-B0, Yolov5m, and ResNet-101 networks have testing accuracies of 98%, 98%, 97%, and 97%, respectively. Thus, all four frameworks have the potential for tomato fruit classification in automated tomato fruit harvesting applications in agriculture.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据