Blankeos / license-plate-detection

🪪 Detect License Plate with YOLOV5, OpenCV, and EasyOCR. Built with PySide and Firebase.

License Plate Detection

A super simple prototype of a license plate detection application.

Built with:

• PySide6 - GUI
• OpenCV - For image transformations
• YoloV5 - For detections (Might upgrade to YoloV8)
• EasyOCR - for OCR detection
• Firebase - For cloud data storage.

Table of Contents

• 📝 Running Requirements
• 🏁 Getting Started
• Resources
• Notes

📝 Running Requirements

• Install Git - On Mac it's already installed.
• Install Python 3.12.2

🏁 Getting Started

Open your terminal and do the following:

1. Git clone and go to directory

git clone https://github.com/Blankeos/license-plate-detection
cd license-plate-detection

2. Create Virtual Env:

python -m venv .venv

2. Activate Virtual Env:

# macOS/Linux
source .venv/bin/activate

# Windows
.venv\Scripts\activate

3. Install Deps

# Install deps for the project.
pip install -r requirements.txt

# Install deps for the model.
git clone https://github.com/ultralytics/yolov5
pip install -r yolov5/requirements.txt

4. Create a file called serviceAccount.json in the root and paste your Firebase Project Service Credentials

   This data is sensitive. Protect it or you risk getting spammed on Firebase.

   💡 How to generate it.

   1. Go to project settings in Firebase.

   2. Generate private key.

   3. Rename it to serviceAccount.json

      // Example `serviceAccount.json`
      {
        "type": "service_account",
        "project_id": "project-id-here",
        "private_key_id": "private-key-id-here",
        "private_key": "private-key-here",
        "client_email": "[e-mail]",
        "client_id": "123456789101112131415",
        "auth_uri": "https://accounts.google.com/o/oauth2/auth",
        "token_uri": "https://oauth2.googleapis.com/token",
        "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
        "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/subdomain.iam.gserviceaccount.com",
        "universe_domain": "googleapis.com"
      }

5. Run the app (It will take a while the first run)

python main.py

Resources

https://realpython.com/python-pyqt-gui-calculator/

Notes

• We use an existing YoloV5 model best.pt from this repo: here.