Scholarlink

Tomatoes are essential agricultural crops throughout the world, but diseases that compromise their yield and quality often affect them. Accurate classification of tomato diseases is crucial for early detection and effective management of pest problems. In this study, we compare the effectiveness of several deep learning models, including ResNet, Inception V3, VGG16, DenseNet and MobileNet, for tomato disease classification. The main objective is to determine which offers the best compromise between accuracy, speed and efficiency. Our results show that ResNet50 is the best choice, with a test accuracy of 98.40% and an F1 score of 98.0%. This outstanding performance makes ResNet50 an effective solution for monitoring and controlling tomato diseases, contributing to the sustainability and productivity of agricultural crops.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Exploring Various Architectures for Tomato Leaf Disease Classification Through Deep Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Hafsa Arid,
  • Insaf Bellamine,
  • Abdelmajide Elmoutaouakkil

摘要

Tomatoes are essential agricultural crops throughout the world, but diseases that compromise their yield and quality often affect them. Accurate classification of tomato diseases is crucial for early detection and effective management of pest problems. In this study, we compare the effectiveness of several deep learning models, including ResNet, Inception V3, VGG16, DenseNet and MobileNet, for tomato disease classification. The main objective is to determine which offers the best compromise between accuracy, speed and efficiency. Our results show that ResNet50 is the best choice, with a test accuracy of 98.40% and an F1 score of 98.0%. This outstanding performance makes ResNet50 an effective solution for monitoring and controlling tomato diseases, contributing to the sustainability and productivity of agricultural crops.