A Novel Model for Automatic Crop Disease Detection

To guarantee food security in the wake of an increasing global population and diminishing agricultural land, detecting and identifying crop diseases early is critical since they are the leading cause of quality and quantity loss. Agriculture is also an essential component of a country's economic strength since it acts as a primary source of income for many people. In precision agriculture, automatic approaches for the early identification of plant diseases have been a hot issue. Plants are always vulnerable to a variety of ailments. These diseases, which viruses, bacteria, or fungus can cause, impair the quality of the crop, resulting in economic losses for those who rely on it directly or indirectly. Several methods for autonomously detecting and diagnosing plant diseases using images of sick and healthy leaves have been proposed with the help of different deep learning models. This work presents a fine-tuned model and performs its performance comparison with VGG16 using the PlantPathology data set. The experimental results show how the proposed model performs better than VGG16.