摘要：Plant diseases are the biggest barrier to the safe production, quality, and sourcing of important agricultural products. As well as diminishing yield, they are of specific concern on account of their immediate effects on human and creature wellbeing. To guarantee negligible misfortunes to the developed yield, it is essential to regulate its development. An abundance of direct and indirect methods of plant disease classification exist, including molecular and serological methods, but they require a considerable amount of manual labor and specialized equipment. The application of image processing techniques and neural network models are reported to enhance agricultural practices and use in quality and safety inspection of various plants. The aim of the proposed system is to employ the use of Convolutional Neural Network models to detect diseases in plants using images of the leaf and providing preventive measures to the user. The networks have been trained on an open dataset of 20,639 images, consisting of 3 different plants in a set of 15 distinct classes including healthy plants. 3 model architectures were trained, with the highest accuracy reaching 99.5%. This work thus demonstrates the feasibility of a leaf disease detection system and can be integrated with the agricultural system to ensure operation in real-time cultivation.
