PREDICTING DIFFERENT TYPES OF PADDY LEAF DISEASES USING CONVOLUTIONAL NEURAL NETWORK

Computer Science and Engineering

In most of the world's are agriculturally dependent countries, paddy farming is the primary source of income. Automated detection of paddy diseases is widely needed in the field of agriculture. Early detection of paddy-related diseases is necessary to protect paddy crops as they can harm the entire farm land. The area of agricultural disease identification has greatly benefited from the recent advances in deep learning approaches. In this study present a unique deep convolutional neural network-based approach for diagnosing three Paddy illnesses such as paddy bacterial leaf blight, paddy blast and paddy brown spot. CNNs are trained to recognize these three rice illnesses by using a dataset of 500 naturally occurring images of damaged and good paddy leaves are taken from a paddy experimental area. The suggested CNNs-based approach obtains an average accuracy for predicting the paddy leaf disease is 0.76 percent. Compared to other standard machine learning models, this effectiveness is significantly greater. The simulated outcomes for identifying paddy illnesses demonstrate the viability and efficiency of the suggested approach.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.