The problem
Grain price depends on quality grades that are assessed by eye, leading to disputes and discounts. Farmers rarely have objective evidence at the point of sale.
What to build
Build an app that photographs a grain sample under a simple light box and reports broken, discoloured and foreign matter percentages with a shareable result.
Success looks like
Grading consistent with a certified lab within an agreed tolerance on 100 samples, and a result record both parties can verify.
Suggested technologies
- Computer vision
- Calibration targets
- Image segmentation
- Mobile app
- Signed results
An original, independent statement. It is not an official Smart India Hackathon problem statement, and Arventiq Labs is not affiliated with or endorsed by that programme. The scenario is illustrative and does not describe any specific organisation. Free to use with credit.