Paper Contents
Abstract
Agriculture is a major source of income and livelihood in many countries. There are numerous food crops, with rice being the most important, particularly in Asian countries, where it is affected by various diseases at various stages. Several diseases affect crop quality and growth. Because some diseases have similar symptoms, it can be difficult to diagnose the disease using traditional methods or with the naked eye at an early stage. An automated system is very useful in detecting disease at the right time, allowing farmers to protect their crops from damage earlier. Deep learning advances have had a major effect on agricultural disease detection. The damage that insects and bacterial diseases to rice plants are well known, and this is a significant issue in areas where rice is a staple food. This study suggests a highly accurate, transfer-learned model that could provide armies and agricultural organizations with a mobile solution for quickly identifying rice leaf illnesses. A generative adversarial network is also used in this study to control the count of disease samples. Furthermore, we contrast our model with other transfer learning architectures. The proposed framework outperformed paradigm classification architectures by more than 80% when tested on transfer learning and CNN algorithms.
Copyright
Copyright © 2023 KARRI SIDDARTHA REDDY. This is an open access article distributed under the Creative Commons Attribution License.
