Researchers at the Pennsylvania State University (PSU) in America are developing a smartphone application that uses image recognition to identify up to 5 different cassava diseases.

The application is being developed and tested in conjunction with the Tanzania research office of the International Institute for Tropical Agriculture (IITA), and a research and development analysis document was published on The Conversation Africa on 1 February.

Cassava remains vulnerable to many viruses and plant diseases and cassava mosaic disease and cassava brown streak disease have become the largest constraints to cassava production in Sub-Saharan Africa, resulting in losses of over US$1 billion per year.

These plant diseases are not new to Africa, and have been causing losses for many decades. However, lack of infrastructure and disease experts means that farmers are not trained to recognise them in the early stages.

“The model is deployed using a mobile device’s camera. What’s novel is that it can run entirely on a smartphone without the need for a wireless connection or access to large processing power.”

Results, based on research recently concluded in Tanzania, showed the app had a 98% accuracy rate (for diseases, pest damage and healthy plants) in field tests. After identifying the disease, farmers are given step-by-step guidance on how to treat the affected plants.

To make it user-friendly for East African farmers, the app has text and voice features in both English and Swahili. It has also been linked to PlantVillage, which is the largest global source of free knowledge on crop and plant health.

Also read:
Weather app for South African small farmers
Farmcrowdy app allows ordinary Nigerians to fund farmers
Dutch calculator can mitigate high input costs for poultry
AfriScout app helps African pastoralists find water and pasture
The future is here – mobile app to connect Zambian smallholder farmers with markets