HTL-TLD: An Improved Hybrid Transfer Learning Based Tomato Leaf Diseases Detection Model

Plants are crucial to society, the environment, and the economy but are susceptible to diseases that threaten agricultural productivity and food security. Early detection of plant diseases is essential to minimize crop losses. Traditional methods are often time-consuming and error-prone, particularly in the early stages. Recently, Artificial Intelligence (AI) techniques, particularly machine learning and transfer learning, have become pivotal for early leaf disease diagnosis. However, these techniques require further improvement. This paper proposes a Hybrid Transfer Learning (HTL) model that combines Transfer Learning (TL) for feature extraction with Machine Learning (ML) for classification to enhance accuracy and efficiency. Using 18,160 images from the PlantVillage dataset, covering nine tomato disease classes, various image enhancement techniques were applied to improve image quality and disease detection performance. The experimental results show that the proposed method achieves a significant accuracy of 99.56%, surpassing that of the current state-of-the-art methods. This approach offers a practical solution for farmers, enabling faster and more accurate disease identification and better crop management.