PADDY PLANT DISEASE DETECTION THROUGH IMAGE PROCESSING USING DEEP LEARNING

Plant diseases are one of the most significant factors that lead to poor yield and a major threat to food security in the agricultural sector.One of the essential parts of cultivation is plant disease detection.Monitoring or taking care of plant diseases manually is very difficult, as it requires an enormous amount of work, planning, and time.As a solution, we can use image-processing techniques to identify and differentiate plant diseases.Plant diseases can be categorized using machine learning and deep learning algorithms through a number of processes, including dataset development, image loading, pre-processing, feature extraction, and classification.Deep learning and machine learning techniques are used in image processing to identify and detect diseases.The detection and classification of plant illnesses can be solved using a variety of deep learning techniques; however, in many regions of the nation, farmers still lack the infrastructure and knowledge necessary to quickly identify plant diseases.Using traditional deep learning (DL) techniques such as feature extraction and classification for plant disease detection, to help farmer's researchers have proposed many DL models to detect diseases in their crops as efficiently as possible to avoid yield loss.The objective of this paper was to construct a model that classifies healthy and unhealthy paddy leaves and identifies the disease using CNN architecture.