Age & Gender Detection - Image Processing Project

A full-stack web application that uses deep learning to detect age and gender from facial images. Built with React frontend and Python Flask backend, powered by a custom MobileNet V2 model.

🚀 Features

• Face Detection: Automatic face detection using OpenCV Haar Cascade
• Age Prediction: Estimates age from facial features
• Gender Classification: Determines gender (male/female) with confidence score
• Modern UI: Beautiful React interface with Tailwind CSS and shadcn-ui
• Real-time Analysis: Fast inference using optimized MobileNet V2 architecture

🏗️ Architecture

Backend

• Framework: Python Flask
• Model: Custom MobileNet V2 with age and gender prediction heads
• Face Detection: OpenCV Haar Cascade
• API: RESTful API with CORS support

Frontend

• Framework: React + TypeScript
• Build Tool: Vite
• UI Library: shadcn-ui components
• Styling: Tailwind CSS

📋 Prerequisites

• Python 3.11+
• Node.js 18+ and npm
• pip (Python package manager)

🛠️ Installation

1. Clone the repository

git clone https://github.com/AlyHesham22/Image-Processing-Project.git
cd Image-Processing-Project

2. Install Python dependencies

pip install -r requirements.txt

3. Install Frontend dependencies

npm install

🚀 Running the Application

Start Backend Server

python app.py

The backend will run on http://localhost:5000

Start Frontend Development Server

Open a new terminal:

npm run dev

The frontend will run on http://localhost:5173 (or similar port)

Test the Model Directly

python Test.py

📁 Project Structure

├── app.py                 # Flask backend server
├── Test.py                # Direct model testing script
├── best_model.pth         # Trained model weights
├── requirements.txt       # Python dependencies
├── package.json           # Node.js dependencies
├── src/                   # React frontend source
│   ├── components/        # React components
│   ├── pages/             # Page components
│   └── ...
└── supabase/              # Supabase configuration (optional)

🧪 Model Details

• Base Model: MobileNet V2 (ImageNet pre-trained)
• Task: Multi-task learning (Age regression + Gender classification)
• Input: 224x224 RGB face images
• Output:
  • Age: Continuous value
  • Gender: Probability score (sigmoid)