A common study issue in the realms of computer vision and agriculture is the detection of illnesses in plants using VGG19 and the ResNet architecture. A model that, using of the plant, can correctly categorize many varieties of rice plant illnesses. The ResNet architecture, a deep learning architecture frequently used for image identification tasks, and the VGG19 architecture, a CNN version, have both demonstrated good accuracy on a variety of image classification tasks. It is necessary to collect a dataset of annotated photos of both healthy and diseased plants in order to train a model for disease identification in rice plants. Each category of disease should have a sufficient number of samples in the dataset for the model to be able to distinguish between them. In order to identify disease features in the photos and categorize the plants as healthy or diseased, the ResNet model uses the VGG19 architecture during the training process. The prototype can be verified using a dissimilar collection of photos when it has been trained to assess in what way fine it achieved. The problem of identifying diseases in plants is addressed by the application of the CNN and VGG16 algorithms in the rice plant disease detection method. The suggested method can precisely diagnose three different classes of plant diseases by gathering and categorizing a dataset of plant photos and training a ResNet model with the VGG19 architecture. This can assist farmers in early disease detection and treatment, lowering crop loss and promoting food security. A cost-effective agricultural monitoring solution can also be provided by combining drone technology, allowing farmers to constantly monitor their crops and quickly identify illnesses. Especially in large-scale agriculture, this method can eliminate the need for manual inspections, which can be costly and time-consuming. The suggested method successfully identified and classified diseases in rice plants with high accuracy, which is a noteworthy accomplishment and demonstrates the value of applying deep learning techniques to agriculture. The approach’s changes also perform better than comparable approaches described in the literature, highlighting its usefulness in real-world settings. Overall, by enabling early diagnosis and treatment of rice plant illnesses, the suggested method using ResNet and VGG19 algorithms, combined with the incorporation of drone technology has the potential to support food security.