Project Info
This project did not submit a demo video on Devpost.
Inspiration
One of our group members had an allergic reaction to food during an outing. The menu did not contain any listed allergens.
What it does
Scans text files (.txt, .pdf, etc), live scans, and photos of menus. Uses text recognition models to identify ingredients in food items. Cross-references with user-provided list of allergens and then recommends to user if food is safe to consume or not.
How we built it
Frontend: React, Tailwind CSS, Vite | Backend: Flask, OpenCV for training data, pytesseract for text recognition module.
Challenges we ran into
Lack of time, lack of experience, connection issues with camera, problems with integrating pytesseract.
Accomplishments we're proud of
Furthered knowledge of AI models, finished despite lack of time, implementation of solution
What we learned
Text detection & recognition, image processing, computer vision, natural language processing.
What's next
Develop a mobile app, partner with restaurants to show allergens on their menus.
FoodAllerGuard
One scan a day keeps the allergies away!
Description
FoodAllerGuard is a web application that analyzes the ingredients in a food item (either via live scan or still photos or text files) and alerts the user if the food item being evaluated contains any allergens or other possibly harmful ingredients.
Tech Stack
-
Frontend
- React (^18.2.0)
- React Router DOM (^7.9.4)
- Tailwind CSS (^3.4.0)
- Vite (^5.0.8)
-
Backend
- Flask (Python)
- Flask-CORS (^4.0.0)
- OpenCV
- pytesseract
Instructions
Installing Dependencies
Frontend (JavaScript)
Navigate to the frontend directory and install dependencies:
cd foodallerguard/frontend
npm install
This will install all JavaScript resources including:
- React (^18.2.0) - UI library
- React DOM (^18.2.0) - React rendering
- React Router DOM (^7.9.4) - Client-side routing
- Vite (^5.0.8) - Build tool and dev server
- Tailwind CSS (^3.4.0) - Utility-first CSS framework
- PostCSS & Autoprefixer - CSS processing
- ESLint - Code linting
- @vitejs/plugin-react - React plugin for Vite
Backend (Python)
Navigate to the backend directory and install dependencies:
cd foodallerguard/backend
pip install -r requirements.txt
Or using pipenv:
pipenv install
This will install:
- Flask (^2.3.3) - Web framework
- Flask-CORS (^4.0.0) - Cross-origin resource sharing
- python-dotenv (^1.0.0) - Environment variables
- pytesseract - OCR for text extraction
- opencv-python - Computer vision library
- Pillow - Image processing
Running the Application
- Start the backend server:
cd foodallerguard/backend
python app.py
- In a separate terminal, start the frontend development server:
cd foodallerguard/frontend
npm run dev
The application will be available at http://localhost:3000
Developers
| Name | Role | GitHub | |
|---|---|---|---|
| Thamizarasu Sankara | Team Lead & Frontend Dev | thamizarasus@gmail.com | thamizarasus |
| Ramanuja Mohanty | Backend Dev | ramanuja.mohanty@gmail.com | RamanujaMohanty |
| David Lei | Backend Dev | DavidtheDefender2003@gmail.com | CaliCanine |
About Us
The concept for FoodAllerGuard began around 2024. We were having lunch at a restaurant when, suddenly, one of our members had an adverse reaction to the item they were eating. After the affected individual received all relevant care, we were able to determine why they had that reaction: the allergens were not clearly listed in the menu. Hence, FoodAllerGuard came into being, a web app (soon to be mobile) that allows users to upload photos of their menus or menu PDFs and learn exactly which allergens are present in the food that can affect them.
Credits
- OpenCV - Training Data
- pytesseract - Image Recognition Module
THANK YOU!
Analysis
View
Metric
- 22
- 6
- 5
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- CSSIn code
- FlaskIn code
- HTMLIn code
- JavaScriptIn code
- PythonIn code
- ReactIn code
- Tailwind CSSIn code
7 of 7 appear in the indexed code.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
92 KB
Source files
27
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
thamizarasus/CalHacks-web
40 files · 93.0 MB · @ 34e2891
Structure
Interface
15 files · 38%Screens, components and styles rendered to the user.
Application logic
13 files · 33%Domain rules, services and shared utilities.
Data & schema
2 files · 5%Schema definitions, migrations and data access.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- JavaScript82%
- Python12%
- Markdown4%
- CSS0%
- HTML0%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
foodallerguard/frontend/package.json
npm · 15- preview
- react
- react-dom
- react-router-dom
- +11 more
foodallerguard/backend/requirements.txt
pypi · 7- Flask
- Flask-CORS
- numpy
- opencv-python
- Pillow
- pytesseract
- python-dotenv
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.