Deep Learning based Automated Wheat Disease Diagnosis System

The conditions of the crop reduce the product and are largely to blame for global profitable losses in agrarian assiduity. The conditions in crops need to be under control and effectively cover in order to improve mortality rates. For image bracketing and recognition, researchers have initially utilized hand-drafted features. Currently, researchers have been able to significantly improve the delicateness of object discovery and bracket thanks to developments in Deep Learning. In this project, we classified wheat conditions with colorful judgments using images captured in situ by camera bias using a deep literacy frame. Stem rust, heroic rust, Powderly rust, and normal are the four orders of wheat complaints that are included in our dataset.207 images were included in each order. Our classifier was trained using a convolutional neural network (CNN). CNN’s ability to automatically reward features by recycling the raw images directly is one of its greatest advantages. Our model achieved a delicacy of 94.54 and can be used by farmers to cover wheat crops against forested conditions.