IoT-Based Disease Detection of Corn Leaf Using CVGG-16 Model

Over the past few years, the Internet of Things (IoT) has garnered significant attention due to its diverse applications. In the agricultural sector, one prominent use case of IoT is smart farming. This innovative approach encompasses various aspects, such as irrigation systems, soil analysis, and crop disease detection. This paper focuses on automating plant disease detection within the IoT environment, particularly targeting the agriculture domain. The proposed system leverages smart cameras deployed in crop fields to capture images of corn leaves. These images are transmitted to a destination node, which employs IoT-based monitoring to gather valuable information about the condition of the corn leaves. For the task of plant disease detection, a CVGG-16 model (CVGG-16) has been developed and utilized. The performance of the CVGG-16 model is compared against other widely used models, including Inception, DenseNet, and VGG-16. A corn leaf dataset is used to evaluate the performance of the proposed VGG-16 model. Remarkably, the proposed CVGG-16 model outperforms all other methods, achieving an impressive accuracy of 97.84%.