Volume 20 No 12 (2022)
 Download PDF
Potato Leaf Disease Detection and Classification using CNN
Dr. Suman Kumar Swarnkar Mr. Abhisek Chakraborty Mr. Arijeet Dutta Ms. Nachiketa Mohanty
All of us are familiar with potatoes as a vegetable. In India, growing potatoes has become quite popular in recent years. However, diseases like early blight and late blight are impeding potato production and driving up production costs. To boost potato production and digitize the system, the goal is to create an automated and quick disease detection method. Our primary objective is to use leaf images to diagnose potato disease using the CNN algorithm. This paper provides a visual representation of how automated systems based on machine learning will identify and categorize potato leaf diseases. The most effective method for identifying and analyzing these disorders is image processing. In this analysis, picture division is carried out; over 2000 images of healthy and unhealthy potato leaf are taken from Kaggle, and a few pre-made models are used to identify and classify healthy and diseased leaves. With 30% test data and 70% train data, the algorithm successfully predicts one of them with an accuracy of 91.41% in testing. Our results demonstrate that CNN outperforms all currently available tasks for detecting potato disease. Soft computing technology is desired by plant pathologists for the precise and dependable diagnosis of plant diseases
Potato disease, late blight, early blight, CNN, image processing, V3, VGG16, VGG19, Feature extraction
Copyright © Neuroquantology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.