Detection of Rice Hispa Disease using a Deep Learning Model

Agriculture is the most important element of the globe and large-scale agricultural operations around the world make it more susceptible to numerous diseases. Rice is one of the most important agricultural plants cultivated in enormous quantities. There are a variety of rice illnesses that impact rice crop plantations in various ways and detecting and recognising them is one of the most difficult tasks. An endeavour has been initiated to use deep learning to recognise rice hispa illness. In order to carry out the experimental work with a real-time dataset of rice hispa and healthy rice crop plant a CNN-based deep learning approach was used. The detection of rice hispa disease was divided into two parts: the first was a binary classification based on healthy and sick plants and the second was a multi-classification based on five severity levels of the disease. The suggested architecture and model serves as a rice disease detection (RDD) system for rice hispa disease assisting farmers and cultivators in recognising and detecting rice crop plants and taking appropriate and timely action.