Image Recognition App

hareerk

A modern full-stack application that combines React and FastAPI to perform image recognition and scene analysis. Using TensorFlow's MobileNetV2 model, the app provides detailed scene descriptions and object recognition with confidence scores. Features a clean, responsive UI built with Tailwind CSS and real-time image analysis capabilities.

Download

Image Recognition and Scene Analysis App

A full-stack web application that performs image recognition and scene analysis using deep learning. The application uses TensorFlow with a pre-trained MobileNetV2 model for image classification and scene description.

Features

Image upload and preview
Object recognition
Detailed scene description
Confidence scores for predictions
Real-time analysis
User-friendly interface

Tech Stack

Backend

Python 3.x
FastAPI
TensorFlow
Pillow (PIL)
uvicorn

Frontend

React
Tailwind CSS
Lucide Icons
Vite

Project Structure

image-recognition-app/
├── backend/
│   ├── app/
│   │   ├── routers/
│   │   ├── services/
│   │   ├── utils/
│   │   └── main.py
│   └── requirements.txt
└── frontend/
    ├── src/
    │   ├── components/
    │   ├── App.jsx
    │   └── main.jsx
    ├── index.html
    └── package.json

Getting Started

Backend Setup

Create and activate virtual environment: ```bash cd backend python -m venv venv

Windows

venv\Scripts\activate

macOS/Linux

source venv/bin/activate


2. Install dependencies:
```bash
pip install -r requirements.txt

Run the server:
```
uvicorn app.main:app --reload
```

The backend will be available at 127.0.0.1:8000

Frontend Setup

Install dependencies:
```
cd frontend
npm install
```
Start the development server:
```
npm run dev
```

The frontend will be available at http://localhost:5173

API Endpoints

GET /: Welcome message
GET /health: Health check
POST /api/v1/image/predict: Image analysis endpoint

Usage

Open the web application in your browser
Click the upload area or drag and drop an image
Click "Analyze Scene"
View the scene description and detailed analysis results

Future Enhancements

Add support for multiple image analysis models
Implement image caching
Add user authentication
Add history of analyzed images
Support for batch processing

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

MIT

Top categories