GastroLens

GastroLens is a mobile application designed to help individuals reduce food waste and find culinary inspiration by utilizing ingredients they already have at home. By simply taking a photo of their fridge or pantry, users receive personalized recipe suggestions powered by AI.

---

📖 Table of Contents

• Problem & Solution
• Key Features
• Tech Stack
• Team & Roles
• Installation & Setup
• Future Roadmap

---

🎯 Problem & Solution

The Problem

Students and people with limited time or cooking experience often struggle to effectively use ingredients they have at home. This leads to:

• Food waste.
• Frequent reliance on fast food.
• A lack of inspiration for creating meals with simple ingredients.

The Solution

GastroLens solves this by offering:

• Visual Recognition: Identification of available ingredients via photo.
• Smart Matching: Personalized recipe proposals based on the percentage of matching ingredients.
• Creativity: Suggestions for enrichment with extra ingredients to encourage experimentation.

---

✨ Key Features

• 📸 Ingredient Detection: Capture a photo using the device camera or upload from the gallery to automatically detect ingredients using the Gemini API.
• 📝 List Management: Edit, add, or remove ingredients from the detected list to ensure accuracy.
• 🍳 Recipe Recommendations: View recipes sorted by ingredient match percentage (e.g., 100%, 85%, 34%).
• 📖 Detailed Instructions: Step-by-step cooking instructions and links to original recipe sources.
• 🖼️ Image Editing: Basic crop and rotate functionality to improve recognition accuracy.

---

🛠 Tech Stack

The project utilizes a modern stack separating the mobile frontend from the AI-powered backend.

Frontend (Mobile App)

• Framework: React Native with Expo.
• Language: TypeScript.
• Navigation: Expo Router (file-based routing).
• UI Components: React Native Paper, Expo Image Picker.

Backend (API)

• Framework: Python (FastAPI).
• AI/ML Model: Google Gemini API (via google-genai) for image analysis.
• Database: SQLite (with FTS for fast recipe search).
• Server: Uvicorn.

---

👥 Team & Roles

• Michael Selvesakis: Backend, Design, Database.
• Dimitrios Manos: Backend, Build/Compile, Testing.
• Gerasimos Charizanis: Frontend.

---

🚀 Installation & Setup

Prerequisites

• Node.js and npm
• Python 3.x
• Google Gemini API Key

1. Backend Setup

Navigate to the backend directory and install dependencies.

cd Backend
pip install -r requirements.txt

Create a .env file in the Backend root and add your API key:

GOOGLE_API_KEY=your_api_key_here

Start the server:

python main.py

The API describes an endpoint /process-image used to analyze photos.

1. Mobile App Setup

Navigate to the mobile app directory.

cd MobileApp/GastroLens
npm install

Start the Expo development server:

npx expo start

You can run the app using the Expo Go app on your physical device or via an Android/iOS emulator.

🔮 Future Roadmap

The team has identified several areas for future expansion:

1. Enhanced Dataset: Incorporating cooking videos and higher-quality recipes.
2. Personalization: Tailoring recipes to user dietary preferences.
3. Health Metrics: Calculation of calories for every recipe.
4. Brand Mapping: Mapping specific brand names (e.g., "Hellman's") to generic ingredient names (e.g., "Mayonnaise").