Scholarlink

For sustaining food security and guaranteeing good crop production, tomato leaf disease must be found. This study examines the efficacy of several ML and DL models for identification. Under various climatic conditions, tomato leaf disease occurs in Bangladesh. TMV, Early Blight, Spider Mites, Late Blight, and Early Blight The dataset utilized in this study includes information on Septoria leaf spots, healthy tomato leaves, and two-spotted spider mite. The AlexNet, ResNet50V2, DenseNet121, InceptionV3, EfficientNet-B4, Support Vector Machine Classification, and ResNet150 models’ recall, accuracy, and precision are compared. The model’s performance is also evaluated in terms of environmental conditions such as occlusion and illumination fluctuations. Our findings provide useful insight into the benefits and drawbacks of various ML and DL models for detecting tomato leaf disease. They also offer recommendations for the creation of disease detection systems that are reliable, accurate, and effective in a variety of environmental conditions.

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

Investigating the Efficacy of ML and DL Models in Detecting Tomato Leaf Diseases under Varying Environmental Factors

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Surendra Reddy Vinta,
  • Yeligeti Raju,
  • P. Nagaraj,
  • K. Ashok Kumar,
  • B. Dhanalaxmi

摘要

For sustaining food security and guaranteeing good crop production, tomato leaf disease must be found. This study examines the efficacy of several ML and DL models for identification. Under various climatic conditions, tomato leaf disease occurs in Bangladesh. TMV, Early Blight, Spider Mites, Late Blight, and Early Blight The dataset utilized in this study includes information on Septoria leaf spots, healthy tomato leaves, and two-spotted spider mite. The AlexNet, ResNet50V2, DenseNet121, InceptionV3, EfficientNet-B4, Support Vector Machine Classification, and ResNet150 models’ recall, accuracy, and precision are compared. The model’s performance is also evaluated in terms of environmental conditions such as occlusion and illumination fluctuations. Our findings provide useful insight into the benefits and drawbacks of various ML and DL models for detecting tomato leaf disease. They also offer recommendations for the creation of disease detection systems that are reliable, accurate, and effective in a variety of environmental conditions.