Hyperlocal Agricultural Disease Detection

Inspiration

We were inspired to leverage the power of AI to provide an accessible, rapid, and accurate diagnostic tool directly to the hands of these farmers,

What it does

Disease Identification: The name of the specific disease detected (e.g., "Early Blight," "Bacterial Spot," "Rust").

How we built it

Backend: Python with Flask/Django for handling API requests, model inference, and data storage.

Challenges we ran into

Photos taken by farmers can vary wildly in lighting, angle, background clutter, and resolution.

Accomplishments that we're proud of

The system provides near-instantaneous disease detection, significantly reducing the time it takes for farmers to get a diagnosis compared to traditional methods.

What we learned

orking on a project that has clear, tangible benefits for a specific community (like local farmers) is incredibly rewarding and motivating.

What's next for Hyperlocal Agricultural Disease Detection

Add more diseases and crop types, especially those critical to the Pimpri-Chinchwad and Maharashtra agricultural landscape.

Built With

• a
• amazon-web-services
• an
• and
• and-data-storage.-machine-learning-framework:-tensorflow/keras-for-building
• and-deploying-our-cnn-model.-database:-a-nosql-database-(like-mongodb)-for-storing-image-metadata
• and-diagnostic-results.-cloud-platform:-initially
• app:
• application
• azure)
• backend:-python-with-flask/django-for-handling-api-requests
• but-for-scalability-and-mobile-integration
• capture
• cloud
• containerization
• cross-platform
• developed
• docker/kubernetes.
• flutter)
• for
• frameworks
• functions/lambda
• google-cloud
• image
• interface
• intuitive
• like
• mobile
• model-inference
• native
• or
• provide
• react
• result
• services
• to
• training
• user
• user-information
• using
• we
• we-deployed-our-model-and-backend-services-on-a-cloud-platform-(e.g.
• we-prototyped-locally
• with