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

作     者：K.Sathya M.Rajalakshmi 

作者机构：Department of Computer Science and EngineeringCoimbatore Institute of TechnologyCoimbatore641014India Department of Information TechnologyCoimbatore Institute of TechnologyCoimbatore641014India 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2022年第42卷第7期

页      面：33-47页

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 0710[理学-生物学] 1002[医学-临床医学] 09[农学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0901[农学-作物学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Super-resolution deep learning interpolation convolutional neural network agriculture rice plant disease classification 

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