RDA- CNN: Enhanced Super Resolution Method for Rice Plant Disease Classification

In the field of agriculture, development an early warning diagnostic system is essential for timely detection and accurate diagnosis diseases in rice plants. This research focuses on identifying plant detecting them promptly through advancements computer vision. The images obtained from in-field farms are typically with less visual information. However, there a significant impact classification accuracy disease due to lack high-resolution crop images. We propose novel Reconstructed Disease Aware–Convolutional Neural Network (RDA-CNN), inspired by recent CNN architectures, that integrates image super resolution into single model classification. network takes low-resolution crops as input employs layers transform super-resolution recover appearance such spots, rot, lesion different parts Extensive experimental results indicated proposed RDA-CNN method performs well under diverse aspects generating visually pleasing outperforms better than other conventional Super Resolution (SR) methods. Furthermore, these subsequently passed deep demonstrate RDA- significantly boosts performance nearly 4–6% compared baseline architectures.