Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Optimized Custom CNN for Real-Time Tomato Leaf Disease Detection

Mangsura Kabir Oni, Tabia Tanzin Prama

TL;DR

This work addresses the need for real-time tomato leaf disease detection by comparing four CNN-based approaches on a field-collected dataset from Bangladesh. The proposed Custom CNN, designed with four 2×2 convolutional layers, dropout, and Xavier initialization, achieved the highest accuracy of 95.2% for healthy vs. diseased leaf classification, outperforming YOLOv5, MobileNetV2, and ResNet18. The study combines end-to-end workflow from field data collection and bounding-box labeling to Grad-CAM interpretation and deployment in a web and Android app, illustrating practical pathways for farmers. The findings demonstrate the potential of a tailored CNN to enable early disease intervention, improve yields, and contribute to sustainable agricultural practices in real-world settings.

Abstract

In Bangladesh, tomatoes are a staple vegetable, prized for their versatility in various culinary applications. However, the cultivation of tomatoes is often hindered by a range of diseases that can significantly reduce crop yields and quality. Early detection of these diseases is crucial for implementing timely interventions and ensuring the sustainability of tomato production. Traditional manual inspection methods, while effective, are labor-intensive and prone to human error. To address these challenges, this research paper sought to develop an automated disease detection system using Convolutional Neural Networks (CNNs). A comprehensive dataset of tomato leaves was collected from the Brahmanbaria district, preprocessed to enhance image quality, and then applied to various deep learning models. Comparative performance analysis was conducted between YOLOv5, MobileNetV2, ResNet18, and our custom CNN model. In our study, the Custom CNN model achieved an impressive accuracy of 95.2%, significantly outperforming the other models, which achieved an accuracy of 77%, 89.38% and 71.88% respectively. While other models showed solid performance, our Custom CNN demonstrated superior results specifically tailored for the task of tomato leaf disease detection. These findings highlight the strong potential of deep learning techniques for improving early disease detection in tomato crops. By leveraging these advanced technologies, farmers can gain valuable insights to detect diseases at an early stage, allowing for more effective management practices. This approach not only promises to boost tomato yields but also contributes to the sustainability and resilience of the agricultural sector, helping to mitigate the impact of plant diseases on crop production.

Optimized Custom CNN for Real-Time Tomato Leaf Disease Detection

TL;DR

This work addresses the need for real-time tomato leaf disease detection by comparing four CNN-based approaches on a field-collected dataset from Bangladesh. The proposed Custom CNN, designed with four 2×2 convolutional layers, dropout, and Xavier initialization, achieved the highest accuracy of 95.2% for healthy vs. diseased leaf classification, outperforming YOLOv5, MobileNetV2, and ResNet18. The study combines end-to-end workflow from field data collection and bounding-box labeling to Grad-CAM interpretation and deployment in a web and Android app, illustrating practical pathways for farmers. The findings demonstrate the potential of a tailored CNN to enable early disease intervention, improve yields, and contribute to sustainable agricultural practices in real-world settings.

Abstract

In Bangladesh, tomatoes are a staple vegetable, prized for their versatility in various culinary applications. However, the cultivation of tomatoes is often hindered by a range of diseases that can significantly reduce crop yields and quality. Early detection of these diseases is crucial for implementing timely interventions and ensuring the sustainability of tomato production. Traditional manual inspection methods, while effective, are labor-intensive and prone to human error. To address these challenges, this research paper sought to develop an automated disease detection system using Convolutional Neural Networks (CNNs). A comprehensive dataset of tomato leaves was collected from the Brahmanbaria district, preprocessed to enhance image quality, and then applied to various deep learning models. Comparative performance analysis was conducted between YOLOv5, MobileNetV2, ResNet18, and our custom CNN model. In our study, the Custom CNN model achieved an impressive accuracy of 95.2%, significantly outperforming the other models, which achieved an accuracy of 77%, 89.38% and 71.88% respectively. While other models showed solid performance, our Custom CNN demonstrated superior results specifically tailored for the task of tomato leaf disease detection. These findings highlight the strong potential of deep learning techniques for improving early disease detection in tomato crops. By leveraging these advanced technologies, farmers can gain valuable insights to detect diseases at an early stage, allowing for more effective management practices. This approach not only promises to boost tomato yields but also contributes to the sustainability and resilience of the agricultural sector, helping to mitigate the impact of plant diseases on crop production.

Paper Structure

This paper contains 16 sections, 6 equations, 9 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Proposed Methodology
  4. Dataset Description
  5. Data Preprocessing
  6. Background Study
  7. Convolutional Neural Networks (CNNs)
  8. YOLOv5
  9. MobileNetV2
  10. ResNet18
  11. Evaluation Metrics
  12. System Architecture of Proposed Model
  13. Experimental Results
  14. Results and Discussion
  15. Conclusion
  16. ...and 1 more sections

Figures (9)

  • Figure 1: Workflow of our proposed mobile application for tomato leaf disease identification
  • Figure 2: Workflow of proposed methodology
  • Figure 3: Example of collected healthy leaf images from field
  • Figure 4: Example of collected diseased leaf images from field
  • Figure 5: Example of data annotating and labeling the raw images
  • ...and 4 more figures