Research: Edge-AI mobile app for crop disease detection
EPIC uses machine learning and artificial intelligence to perform real-time identification of crop disease through a photo-powered app.
Research summary
Research summary
- June 2018 to September 2019
This project builds on our previous research and prototype by developing a mobile app that can identify crop disease.
Our mobile application EPIC is capable of performing real-time disease detection using artificial intelligence and advanced machine learning techniques, even without an internet connection.
Potatoes are the fourth most important food crop in China. Disease detection is an expensive and time-intensive process, and prone to human error.
With little training, farmers can use the tool to access quick and immediate treatment options for the control of potato disease.
Initially, EPIC will be used in Hebei Province to protect a planting area spanning 25,000 hectares.
Our artificial intelligence models are capable of detecting three major potato diseases - late and early blight, and June disease - and are constantly refined through new images acquired from users to ensure ongoing accuracy.
View the mobile application
Watch our walkthrough showing how our app uses artificial intelligence to detect late and early blight, and June disease.Research outputs
- Academic papers, reports and other research outputs will be linked from here when they are published.
Research team
With funding from
With funding from
Biotechnology and Biological Sciences Research Council
Global Challenges Research Fund
contact
Contact us
For general enquiries about this project and our Data Science research theme, you can contact Prof Liangxiu Han.
