PLANT CHECK: POTATO LEAF DISEASE DETECTION USING CNN MODEL

Abstract

Agriculture accepts a basic part by virtue of the quick improvement of the general population and extended interest in food in India. Hence, it is required to increase harvest yield. One serious cause of low collect yield is an infection brought about by microorganisms, infection, and organisms. Potatoes are a well-known vegetable to all of us. Potato cultivation has been very popular in India form the last few decades. But potato production is being hampered due to diseases like early blight and late blight which are increasing the cost of production. The objective of this research is to establish an efficient and expedited process for detecting diseases in potatoes, with the aim of boosting potato production and digitizing the existing system. Our primary aim is to diagnose potato diseases by utilizing a CNN algorithm to analyse leaf images. This study presents an automated system, based on image processing and machine learning, for the detection and classification of potato leaf diseases. Image processing emerges as the most effective approach for identifying and analysing these diseases. To conduct this analysis, our team divided more than 2000 leaf pictures of healthy and unhealthy potatoes, obtained from the Kaggle platform. We incorporated several preprepared models to accurately identify and classify healthy and diseased leaves. Through rigorous testing, the program demonstrated an impressive accuracy of 91.41%, using a 30% test data and 70% train data split. The dataset used in this study was sourced from the renowned public data repository, Kaggle, specifically the "Plant Village" dataset.