Potato Plant Leaf Disease Diagnosis System
Student: Ezra Andrew (Project, 2025)
Department of Computer Science and Informatics
Kaduna State University, Kaduna, Kaduna State
Abstract
Potatoes are one of the world’s most important food crops, but they are vulnerable to various diseases that can reduce yield and quality. Many farmers in Nigeria still rely on manual inspection and random chemical application, which are often ineffective. This study introduces a Potato Plant Leaf Disease Diagnosis System that uses deep learning to improve disease detection. The system is powered by the EfficientNetB7 Convolutional Neural Network (CNN), a highly accurate model for image classification. The model was trained on a dataset of potato leaf images and achieved 98% accuracy on the test set and 97.5% validation accuracy, proving its reliability. The system is available as a web application, allowing farmers to upload or capture leaf images, get a diagnosis, and receive treatment advice. By providing a fast and accurate diagnosis, the system helps farmers make better decisions, improve crop health, and reduce losses.
Keywords
For the full publication, please contact the author directly at: ezraandrew@gmail.com
Filters
Institutions
- Covenant Polytechnic, Aba, Abia State 1
- Covenant University, Canaan Land, Ota, Ogun State 4
- Crawford University of Apostolic Faith Mission Faith City, Igbesa, Ogun State 2
- Crescent University, Abeokuta, Ogun State 1
- Cross Rivers University of Technology, Calabar, Cross Rivers State 142
- Delta State Polytechnic, Ogwashi-Uku, Delta State 11
- Delta State Polytechnic, Otefe, Delta State 12
- Delta State University, Abraka, Delta State 139
- Ebonyi State University, Abakaliki, Ebonyi State 17
- Edo University, Iyamho, Edo State 10