User

Mobile

Desktop

Tablet

Frontend: React + Tailwind

Web Speech TTS · Accessibility features

camera capture multi-frame

capture, results

• POST /api/detect

• GET /api/products

Routing and endpoints

resize / enhance / crop

products.json / Postgres

Logging / fallback

YOLOv8 (detection) + pyzbar (barcode)

Inputs: image frame | Outputs: product key, confidence.

Data Storage

Tech Stack

Frontend: React, Tailwind

Backend: Flask, ultralytics

AI: YOLOv8, pyzbar, pytesseract

DB: products.json / Postgres

Dev: VS Code, Docker (optional)

Barcode = deterministic (high confidence)

YOLO = probabilistic (confidence score)

OCR = fallback (text match)