Early stage Potato Disease Classification by analyzing Potato Plants using CNN

Potatoes are one of the most popular edible plants worldwide. Potato cultivation in Bangladesh has gained wide recognition in recent decades. The healthy development of potato plants is hampered by numerous illnesses The appearance of the disease can be seen on the plant's leaves. Two of the most common leaf diseases affecting the potato flora are late blight and early blight. If these illnesses were detected early enough, they could yield better results. Detecting and analyzing potato leaf diseases using a computer-based image processing technique is an ideal alternative. This paper aims to develop a system that can be used to classify and identify these diseases & presents an image segmentation procedure that involves analyzing over 2152 photos of healthy and problematic potato leaves. Comparing seven classifier algorithms, it identified the types of leaves most likely to be affected by the diseases. The Convolutional neural network is one of the most accurate of the algorithms used. Based on the data gathered about the plant leaves, we suggested a method that may identify the existence of illnesses in potato plants. Farmers and agricultural managers who want to find illnesses in their crops may find this method valuable. In this study, we will explore the use of the CNN framework to develop a strategy that can improve the accuracy of our method.