🌱 GreenGuide - iOS

📱 Overview

GreenGuide is an AI-powered waste management iOS application that helps users make environmentally conscious disposal decisions. Simply snap a photo of any item, and GreenGuide uses advanced computer vision and reasoning models to identify the object, determine the proper disposal method, and provide personalized environmental impact feedback.

Backend Repository: GreenGuide Backend

✨ Features

🎯 Core Functionality

• Smart Image Classification: Real-time object identification using NVIDIA's Nemotron AI models
• Multi-Category Disposal: Classifies items into 6 categories (Recyclable, Compostable, Landfill, Hazardous, E-waste, Textile)
• Preparation Guidance: Step-by-step instructions for proper item preparation before disposal
• Confidence Scoring: Transparent AI confidence levels (High/Medium/Low) for each classification

📊 Impact Tracking

• Local History Storage: SwiftData-powered persistent storage of all scanned items
• Statistics Dashboard: Real-time visualization of environmental impact metrics
• Category Breakdown: Visual progress bars showing disposal distribution
• Environmental Metrics: Track CO₂ savings, energy conservation, water saved, and more

🎨 User Experience

• Native iOS Design: Built entirely with SwiftUI for smooth, modern interactions
• Camera & Photo Library: Seamless integration with iOS photo capabilities
• Dark Mode Support: Automatic adaptation to system appearance
• Animated Launch Screen: Polished first-impression experience

🏗️ Architecture

Tech Stack

• Language: Swift 5.9
• UI Framework: SwiftUI 3.0
• Data Persistence: SwiftData (iOS 17+)
• Networking: URLSession + async/await
• Image Processing: UIKit ImagePicker, CoreImage
• Backend API: RESTful FastAPI service

Project Structure

GreenGuide/
├── Models/
│   ├── ScanRecord.swift          # SwiftData model for scan history
│   └── APIService.swift          # Network layer & API responses
├── Views/
│   ├── LaunchScreen.swift        # Animated launch screen
│   ├── MainTabView.swift         # Tab navigation container
│   ├── ScanView.swift            # Main scanning interface
│   ├── HistoryView.swift         # Scan history & detail views
│   └── ImpactDashboardView.swift # Statistics & impact tracking
├── Components/
│   ├── ImagePicker.swift         # UIKit-SwiftUI bridge
│   ├── CategoryCard.swift        # Reusable category display
│   └── ConfidenceBadge.swift     # Confidence level indicator
└── GreenGuideApp.swift           # App entry point

🚀 Getting Started

Prerequisites

• macOS 13.0 or later
• Xcode 15.0 or later
• iOS 17.0+ device or simulator
• Active GreenGuide backend instance

Installation

1. Clone the repository

   git clone https://github.com/elisha-et/greenguide-ios.git
   cd greenguide-ios

2. Open in Xcode

   open GreenGuide.xcodeproj

3. Configure Backend URL

   In APIService.swift, update the backend URL:

   static let baseURL = "YOUR_BACKEND_URL"
   // Example: "https://greenguide-backend.onrender.com"

4. Build and Run

   • Select your target device/simulator
   • Press ⌘ + R to build and run
   • Grant camera and photo library permissions when prompted

Backend Setup

This app requires the GreenGuide backend service. Follow the setup instructions at: GreenGuide Backend Repository

📸 Screenshots

Scan View	Results	History	Dashboard

📊 Data Models

ScanRecord (SwiftData)

@Model
final class ScanRecord {
    var id: UUID
    var date: Date
    var objectName: String
    var category: String
    var categoryIcon: String
    var categoryColor: String
    var confidence: Double
    var environmentalFeedback: String
    var primaryMetric: String
    var preparationSteps: [String]
    var imageData: Data?
}

API Response Structure

struct ClassificationResponse: Codable {
    let success: Bool
    let is_waste_item: Bool
    let object: String?
    let category: String?
    let category_info: CategoryInfo?
    let preparation_steps: [String]?
    let confidence: Confidence?
    let environmental_impact: EnvironmentalImpact?
}

🎯 Features Roadmap

• Export Functionality: Share impact statistics as images
• Notifications: Reminders for recycling days
• Community Features: Compare impact with friends
• Offline Mode: Cache classifications for offline access
• AR Mode: Point camera at items for real-time classification
• Location-Based Tips: Local recycling center information
• Multi-Language Support: Internationalization

🧪 Testing

Manual Testing

1. Test camera capture with various lighting conditions
2. Verify photo library integration
3. Test with edge cases:
   • Blurry images
   • Multiple objects
   • Non-waste items (people, landscapes)
4. Validate data persistence across app restarts
5. Test deletion and history management

Test Coverage

• Unit tests for API response parsing
• SwiftData CRUD operations
• Image processing pipeline

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

---

Made with 💚 and ♻️ for a sustainable future