TOWARDS FOOD SECURITY THROUGH ARTIFICIAL NEURAL NETWORK

Abstract

Abstract The detection of plant disease is a very important factor to prevent serious outbreak. The Outbreak of disease in paddy plant could cause severe losses in yield leading to insecurity of food security. To achieve automatic diagnosis of paddy disease this research aims to develop a system for detection of Blast disease in paddy leaf. The disease identification is achieved through Image Processing technique and Back Propagation Neural Network. Features of images are extracted through binning pixels into eight Attribute Bins. Training of Neural Network is achieved by feed forwarding these features to neural network. The error generated is back propagated in order to adjust the weights of neural network. Images of the diseased leaves are identified with accuracy. Thus fast and accurate diagnosis of paddy disease could timely control outbreak leading the path towards ensuring food security. This research could be enhanced through implementation of Deep Learning Neural Network, further contributing the Smart Agriculture