Potato Leaf Disease Detection System Using the Convolutional Neural Network (ResNet)

Potato is a crucial crop on a global scale, and its productivity can be impacted by a range of diseases, including leaf diseases. Timely identification and precise diagnosis of leaf diseases can play a crucial role in preventing their rapid dissemination and mitigating potential crop damages. Over the past few years, Convolutional Neural Networks (CNNs) have demonstrated remarkable capabilities in image classification tasks, such as identifying diseases in plants. Our study presents a method for effectively identifying potato leaf diseases, including early blight, late blight, and healthy leaves. We utilize a CNN model that is built on the ResNet architecture, ensuring professional and accurate results. Through the utilization of this model, our objective is to effectively classify and detect diseases in potato leaves, enabling the implementation of timely and efficient disease management strategies. The dataset contains images of healthy leaves as well as leaves that have been infected with various diseases, including early blight and late blight. The model is then utilized to categorize new images of potato leaves as either healthy or diseased. The proposed approach demonstrates a high level of accuracy, achieving 97.9% in the classification of potato leaf diseases, including early blight potato leaf disease and late blight potato leaf disease