<![CDATA[Rice (Oryza sativa) is one of the world's main food crops as it serves as a staple food source for the majority of people in various countries, including Indonesia. Optimal rice productivity is highly dependent on plant health, particularly the condition of the leaves, which are susceptible to various diseases. Diseases affecting rice leaves can significantly reduce yields, making early detection and disease management crucial for farmers. Deep learning methods, such as Convolutional Neural Networks (CNNs), have demonstrated excellent performance in image pattern recognition, including plant disease classification based on leaf imagery. One of the latest advancements in this field is Compact Convolutional Transformers (CCT), which combine the strengths of CNNs in capturing local features with the ability of Transformers to understand global relationships between image features. The Compact Convolutional Transformers (CCT) method will be applied to classify rice plant diseases based on leaf images. This study classifies four categories, namely Normal, Leaf smut, Brown spot, and Bacterial leaf blight. This technology is expected to assist farmers in detecting rice diseases automatically and more rapidly, ultimately enhancing productivity and harvest quality. The study has resulted in a reliable model, achieving an accuracy of 94% with a low loss.]]>
Copyrights © 2025
