← Back to Publications List

Tomato Leaf Disease Detection Using Deep Learning-Based Image Classification

Students & Supervisors

Student Authors
Md. Zahidul Haque
Master of Science in Computer Science, FST
Yousha Rashid
Bachelor of Science in Computer Science & Engineering, FST
Supervisors
Dr. Firoz Ahmed
Professor, Faculty, FST

Abstract

Tomato crops are highly susceptible to a wide range of leaf diseases, including Early Blight, Late Blight, Leaf Mold, Septoria Leaf Spot, Bacterial Spot, Tomato Mosaic Virus (ToMV), and Tomato Yellow Leaf Curl Virus (TYLCV). These diseases significantly reduce crop yield and fruit quality, leading to substantial economic losses for farmers worldwide. Effective disease management depends on early and accurate diagnosis, particularly in field environments where environmental variability makes manual inspection challenging. Traditional visual assessment methods are time-consuming, subjective, and often unreliable during early infection stages. This study proposes a hybrid Tomato Leaf Disease Diagnosis and Treatment Recommendation System that integrates a YOLOv8-based deep learning model with a rule-based Knowledge-Based System (KBS). The YOLOv8 model performs real-time localization and classification of diseased regions using both publicly available datasets and real-field images captured under natural conditions. Following detection, the KBS generates structured treatment recommendations, including chemical and organic control strategies, dosage instructions, and preventive measures derived from expert knowledge. Experimental results demonstrate that the proposed system achieves a mean Average Precision (mAP@0.5) of 91.7%, with balanced precision and recall performance across multiple disease categories. By combining automated detection with actionable treatment guidance, the framework provides a scalable and practical solution for precision agriculture and fieldlevel disease management.

Keywords

Modeling Diseases Signal detection Knowledge based systems Printing Timing Location awareness Accuracy Real-time systems Convolutional neural networks

Publication Details

  • DOI: 10.1109/QPAIN69676.2026.11545607
  • Type of Publication:
  • Conference Name: IEEE International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN 2026)
  • Date of Conference: 16/04/2026 - 16/04/2026
  • Venue: Chittagong University of Engineering and Technology (CUET), Chittagong, Bangladesh
  • Organizer: IEEE Photonics Society Bangladesh Chapter
View on Publisher