Automated Rice Leaf Disease Detection using Advanced Deep Learning Algorithms: A Study
Sivakumar Rajendran
Abstract
For billions of people around the world, rice serves as their primary food source, making it crucial to global food security. However, brown spot and other diseases have a significant influence on agricultural output, which highlights the need for precise and efficient diagnostic methods. This study presents a deep learning-based technique for dividing rice leaves into groups that are healthy and those that have brown spot. This work employed two convolutional neural network architectures, Xception and Mobilenet, to evaluate their performance in this categorisation test. MobileNet demonstrated its exceptional accuracy of 94.68%, demonstrating its capacity to deliver findings with remarkable precision. Xception offers a lightweight and computationally efficient substitute with an accuracy rate of 88%, making it ideal for resource-constrained scenarios. It is shown how deep learning models can be included into automated disease detection systems.