Potato and Maize Plant Disease Detection Using Leaf Images

Abstract

Plant diseases represent a serious threat to national productivity and global food security. Effective therapy for multiple diseases requires a precise and useful differentiation of them. In this work, a computerized system for the identification and categorization of diseases in potato and maize crops is developed using convolutional neural networks. The demonstration was created with the ResNet50V2 model and tested on a combined collection of images of leaves. The system achieved an astounding accuracy of 85.19. Enhancing model execution through exchange learning, fine-tuning, and information augmentation were all part of the process. With the use of another dataset, the trained model was verified and produced positive results, almost exactly differentiating between the disease-causing leaf type (potato or maize). This technology helps ranchers adopt sustainable and knowledgeable disease management methods by promoting timely mediations, which in turn advances disease discovery.

Code and data availability

The paper uses two publicly available Kaggle leaf-image datasets and a ResNet50V2 model, but provides no deposit links, author code, trained checkpoints, or supplementary assets. The Kaggle datasets are generic public inputs, not paper-specific deposits with author URLs, so no qualifying asset is present.

No evidence-backed public reproduction asset is currently recorded.