An Effective Model for Detecting Severeness of Disease in Paddy Leaf

The capacity to recognize and classify diseases based on leaf images acquired from plants is necessary. Using image processing algorithms to detect diseases in rice leaves would reduce reliance on farmers to preserve agricultural goods. The research paper uses image processing to identify and diagnose sickness in paddy leaves. An innovative neural network-based technique for identifying and categorizing rice leaf disease is given in this paper. Advanced mechanisms have employed an approach that incorporates photo compression, edge detection, and a neural network to perform sickness diagnosis rapidly and reliably. The proposed model accuracy is greater than accuracy found in previous studies. Furthermore, the recommended model, which employs a neural network and a edge detection algorithm, has greater precision and recall accuracy than the previous model for bacterial blight, brown spot, health, and rot. Finally, compared to the previous technique, the proposed model is more accurate, adaptive, and scalable. Furthermore, research has concentrated on simulating the disease’s intensity. There are three scenarios that are taken into account. One is when there is no sickness present. The second scenario is a situation in which the sickness has been identified but is not severe and is treatable. The third scenario depicts a circumstance in which the identified sickness is severe yet curable.