Potatoes are the world's famous vegetable. A significant issue for potatoes is the identification of potato leaf disease. The leaves of potato plants display the signs of several illnesses, such as early blight, late blight, and others. Early detection of these outbreaks and quick action can prevent the farmer from suffering significant financial losses. Our proposed model would employ image processing techniques to accurately identify and categories potato leaf diseases. This study uses the CNN (Convolutional Neural Network) model, which is used for image classification and performs better than other approaches in terms of accuracy, to detect disease in images of potato leaves. This model separates potato leaf characteristics into normal and diseased ones. The potato plant leaf is classified as either normal or unhealthy after the images are evaluated using the provided algorithm. This experiment has achieved an average accuracy of 98%.