Tomato Leaf Disease Detection using Lightweight Deep Convolution Network

Plant diseases are the most significant dangers to the nation's food supply and the decline in agricultural output; yet, the rapid identification of plant diseases continues to be difficult due to a lack of availability of the appropriate infrastructure. It is possible to see the symptoms of the crop disease in a variety of components of the crop; however, the leaves exhibit signs of the illnesses that are particularly relevant. Distinct computer visionbased approaches that are used successfully for the plant leaf disease detection (PLDD). In this study, a comprehensive assessment of PLDD methodologies that make use of a different of machine learning (ML) and deep learning (DL)-based techniques is presented. It is focused on the positive and negative aspects of the study. Additionally, we have assessed the results of PLDD system for deep convolution neural network. The DCNN based PLDD offers the accuracy of 95.50%, recall of 0.97, precision of 0.95 and F1-score of 0.96 for Plant Village dataset.