Public Protocol
Platform

Paper

Deep learning for image-based cassava disease detection (Ramcharan and others, 2017)

External resource. Not made or verified by Public Protocol.

Transfer learning on field photographs of cassava leaves taken in Tanzania, with uncontrolled backgrounds, to recognise three diseases and two kinds of pest damage. The paper reports 93 per cent overall accuracy on data not used in training and models that run on Android phones.

Go to the source

https://www.frontiersin.org/articles/10.3389/fpls.2017.01852/full

Maintainer
Frontiers in Plant Science; the authors
Licence, as stated at its source
Creative Commons Attribution (CC BY 4.0)
Open or commercial
Open
Maturity
WorkingOur reading, 16 November 2026
Safety
S0
Review
Listed 16 November 2026by Public Protocol editors
Checked
16 November 2026
Next check due
16 May 2027
Steward
Public Protocol editors

Where it sits in the blueprint

Stages

Learn, Deploy

Context

Climate, setting, scale, cost and skill: not stated in this entry. Check the source against your own place and numbers.

Verification

No verification is recorded on Public Platform for this entry. Records are added when someone reads it for accuracy, reviews it with a stated qualification, builds it or measures it.

Record

How it came in

Seed catalogue, 16 November 2026. Listed from open research on agriculture and smart farming. The source was opened and described on the date shown.

Licence

Creative Commons Attribution (CC BY 4.0). Read at https://www.frontiersin.org/articles/10.3389/fpls.2017.01852/full. How licences are recorded