What I Eat: Food Allergen Scanner
On-device OCR and ingredient classification for dietary safety.
Project Profile
Technologies
This project features automated end-to-end regression runs checking auth flows, payment syncs, and telemetry channels prior to production release.
01 / The Challenge
Users with food allergies or dietary restrictions must scan tiny ingredient lists, which is slow and prone to human error.
02 / Our Solution
We optimized Apple's Vision framework for on-device OCR, extracting text from curved packaging. The ingredients are parsed against user dietary profiles locally, with OpenAI API classification for complex food additives.
03 / System Outcome
What I Eat enables users to scan and verify food safety in under 2 seconds, detecting allergens with high accuracy.
System Architecture & Data Flow
Discuss a similar scale-up project
Ready to optimize your product architecture or automate system telemetries? Let's talk.