Classification of Tomato Crop Diseases by utilizing Convolutional Neural Network

The farming sector has significant challenges posed by plant diseases, resulting in extensive crop devastation and substantial financial repercussions. Precise and prompt diagnosis is essential for efficiently managing and preventing several diseases. Deep learning has become a major technique in image processing, providing strong and reliable solutions while being relatively new. Diverse advanced deep learning techniques have been used to identify and categorize leaf diseases. This article discusses a particular approach that use deep learning to detect diseases in tomato crops. The concept centers on the use of convolutional neural networks (CNN) for the purpose of identifying and categorizing illnesses. The model's structure comprises of two convolutional layers and two pooling layers, ultimately leading to a fully linked layer at the end. The training and validation dataset is obtained from the Division of Plant Pathology of the Indian Agricultural Research Institute, situated in New Delhi. The dataset is acquired by the use of a high-resolution camera. The experimental results clearly demonstrate the effectiveness of the suggested technique, highlighting its superiority compared to past research efforts. The model has outstanding precision in its annotations, obtaining an impressive degree of accuracy at 96.88%.