An Improved Deep Learning Model for Classification of the Multiple Paddy Disease

Each year, rice crops are seriously damaged by several rice diseases all over the world. The prediction of rice plant diseases early and accurately has proven to be a difficult task for farmers and academics. The field of convolutional neural networks (CNNs) has recently undergone significant development that has increased the convenience and accuracy of image processing methods. This study suggests three types of rice plant diseases can be detected using a blended CNN-based classification model. Furthermore, two alternative models KNN and SVM were evaluated in terms of their effectiveness in detecting illnesses in rice plants. It has been observed that the proposed model outperforms alternative models that are currently being used. In the experimental analysis, It has been shown that the suggested model can accurately diagnose illnesses in rice plants with a 99% accuracy rate and a reduction in model size.