PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Major Project
Medicine Label Scanner with OCR
Photograph a strip, read the drug name, look up uses and side effects
2-3 weeks build
Overview
A mobile app that captures a medicine strip or carton, cleans the image with OpenCV, reads the printed text with OCR and fuzzy-matches the brand or salt name against a drug table. The result screen shows uses, typical dosage guidance and common side effects, with a clear note to follow the prescriber.
What makes it stand up
- 01Preprocessing for glare, curved foil and low light before OCR
- 02Fuzzy matching that tolerates OCR misreads of brand names
- 03Salt-level lookup so generics and brands resolve to the same entry
- 04Drug table seeded from public sources such as openFDA labels
- 05Information-only screens that defer to the prescriber and pharmacist
Module breakdown
- 01
Capture
Flutter camera screen with crop guide and retake flow.
- 02
Image cleanup
Deskew, adaptive threshold and glare suppression.
- 03
OCR and matching
Tesseract text read plus edit-distance name matching.
- 04
Drug database
Normalised brand, salt, use and side-effect tables.
- 05
Evaluation
Character error rate and match accuracy on a labelled photo set.
After this, you will be able to
- Explain why preprocessing matters more than the OCR engine choice
- Defend your fuzzy-matching threshold with measured error cases
- Demo a live scan from phone camera to drug information
Technology stack
- Python
- OpenCV
- Tesseract
- FastAPI
- Flutter
- PostgreSQL
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 2-3 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support