Classification of tomato leaf images for detection of plant disease: A Comprehensive Review

Arjunan, Viswanathan and Deenan, Surya Prabha (2025) Classification of tomato leaf images for detection of plant disease: A Comprehensive Review. International Journal of Science and Research Archive, 14 (3). pp. 1124-1129. ISSN 2582-8185

Tomatoes are one of the most extensively cultivated vegetable crops in India, and they benefit from the country’s tropical climate. However, various environmental factors, including fluctuating climatic conditions and plant diseases, significantly impact its growth and yield. Among these challenges, plant diseases pose a major threat, leading to substantial economic losses. Traditional methods for disease detection in tomato plants have proven inefficient due to their delayed diagnosis and limited accuracy. Early identification of diseases can help mitigate crop losses and improve yield quality. To address this issue, advanced computer vision and deep learning techniques offer promising solutions for early and accurate disease detection. This study provides a detailed analysis of different machine learning-based approaches for tomato leaf disease classification, highlighting their advantages and limitations. Additionally, the paper proposes a hybrid deep-learning model CNN, RNN, YOLOv8 are designed to enhance early detection accuracy and improve disease management strategies in tomato cultivation.