ABSTRACT
Plants play a vital role in supplying food globally. Various environmental variables lead to plant ailments, which result in significant production losses. However, manual detection of plant diseases is a time-consuming process, and conventional methods of disease detection are often labor-intensive and require expert knowledge. Many solutions were devised using the Internet of Things wherein sensors were used to record data and process them using simple algorithms. There are very few solutions that focus on the processing of data to diagnose plant diseases. In an attempt to offer a more effective solution, this study investigates the use of deep learning techniques to create a model that diagnoses plant diseases based on leaf images. In order to identify and categorize crop diseases from leaf images, this study makes use of convolutional neural networks, a type of deep learning method specialized in image detection. There are many benefits to applying this disease detection technique based on deep learning to precision agriculture techniques. It makes early diagnosis and real-time monitoring possible, allowing timely action and lowering the need for pharmacological treatments. Reducing the negative effects on the environment not only improves crop health and yield but also supports sustainable agricultural methods.
