Early Detection of Disease in Rice Paddy: A Deep Learning based Convolution Neural Networks Approach

Abstract

The agriculture industry faces huge economic losses due to bacterial, viral or fungal infections in the crops due to which farmers lose 15 to 20% of their total profit every year. India is the second largest producer of rice and a leading exporter of the same in the global market. Thus, early detection of diseases in essential crops is a significant area of research in order to prevent further damage to them. The widespread development of Deep Learning makes it possible to achieve the goal of disease detection in crops. The novelty of this work is early detection of Brown spot disease in rice paddy using Convolution Neural Networks. The area of the disease affected was also found to optimize the usage of fertilizers. This work makes use of Image recognition and preprocessing algorithm based on real time data. Data preprocessing and feature extraction has been done using a self-designed image-processing tool. Tensor flow and Keras framework has been implemented on both training and testing data which was collected manually from rice fields. The proposed model achieved an accuracy of 97.32%.