How akashkobal/arecanut-diseases-detection works
The repository presents an arecanut disease-detection web app: a farmer selects an image, the frontend posts it to a prediction API, and the UI displays a label, confidence, and treatment guidance. The API and model artifact are present, but their invocation relationship is not visible in the supplied source excerpts, so that link is marked unverified. The README also describes CNN-based detection and actionable remedies; the report page is a separate frontend feature. Other publication-site pages appear unrelated to the documented product.
Main entry points: Report.js Report page · App.js Route application · main.py Prediction API · home.js Image upload
Components 11
Web client
- Route application
frontend/src/App.js - Image upload
frontend/src/home.js - Prediction display
frontend/src/home.js - Navigation bar
frontend/src/Components/Navbar.js - Footer
frontend/src/Components/Footer.js - Browser entry
frontend/src/index.js
Inference
- Prediction API
api/main.py - CNN model
models/1/saved_model.pb
Project report
- Report page
frontend/src/Components/Report.js - HTML renderer
frontend/src/Components/HtmlRenderer.js
Other components
- Farmer
Connections 10
- Farmer → Image upload: selects image
frontend/src/home.js - Browser entry → Route application: renders
frontend/src/index.js - Route application → Image upload: routes to
frontend/src/App.js - Route application → Report page: routes to
frontend/src/App.js - Image upload → Prediction API: posts image
frontend/src/home.js - Prediction API → CNN model: uses model
- Prediction API → Prediction display: returns prediction
- Report page → HTML renderer: renders content
frontend/src/Components/Report.js - Report page → Navigation bar: renders
frontend/src/Components/Report.js - Report page → Footer: renders
frontend/src/Components/Report.js