RoboVAI OCR 🚗🆔👤

RoboVAI OCR is a high-performance, enterprise-grade Computer Vision and OCR framework built for Automatic License Plate Recognition (ALPR), National ID Card Parsing, and Driver Facial Verification.

Designed for seamless deployment in Smart Parking Systems, Barrier Gate Controls, Fleet Management, and Access Security, RoboVAI OCR provides an intuitive Python SDK, a high-throughput Async Pipeline, and a production-ready FastAPI REST & WebSocket Server.

🖥️ Live Control Center Dashboard

🔥 Key Capabilities

• Automatic License Plate Recognition (ALPR): Multi-scale inference (TTA) with region-split whitelisted OCR for Egyptian, Arabic, and international vehicle plates.
• National ID & Driver License Parsing: End-to-end deep learning OCR extracting 14-digit Egyptian National ID, Full Name, Address, DOB, Gender, Governorate, and photo crop.
• Driver Facial Verification: Real-time facial feature extraction and authorization matching against a driver registration database.
• High-Concurrency RTSP / Stream Processing: Async queue architecture decoupling object tracking from heavy OCR background execution.
• Developer First: Clean Python SDK, interactive Web Dashboard, CLI tools, OpenAPI docs, and Webhooks for automated hardware/barrier control.

⚡ Quick Start

Installation

Install the latest release directly from PyPI:

pip install --upgrade robovai-ocr

Or install from source for development:

git clone https://github.com/m0shaban/robovai_ocr_system.git
cd robovai_ocr_system
pip install -e .

💻 Developer Guide & Usage Examples

1. Python SDK Integration

from robovai_ocr import RoboVAIEngine

# Initialize engine (auto-detects CPU/GPU)
engine = RoboVAIEngine()

# --- License Plate Recognition ---
plate_res = engine.read_license_plate("car.jpg")
print(plate_res["plate_number"])  # e.g. "س ط أ 1 2 3"
print(plate_res["confidence"])    # e.g. 0.96

# --- Egyptian National ID Extraction ---
id_res = engine.extract_national_id("national_id.jpg")
print(id_res["national_id"])     # e.g. "29901010100123"
print(id_res["full_name"])       # e.g. "أحمد محمد علي"
print(id_res["governorate"])     # e.g. "Cairo"

# --- Driver Face Verification ---
face_res = engine.verify_driver_face("driver.jpg", db_path="data/driver_faces")
print(face_res["match"])         # True / False

2. High-Throughput Async Pipeline

import asyncio
from robovai_ocr.core.pipeline import AsyncOCRPipeline

async def main():
    pipeline = AsyncOCRPipeline()
    await pipeline.start()
    
    # Submit frame for non-blocking processing
    job_id = await pipeline.submit_frame(frame_bytes)
    result = await pipeline.get_result(job_id)
    print(result)

asyncio.run(main())

3. Command Line Interface (CLI)

# Run ALPR on single image
robovai-cli alpr --image path/to/car.jpg

# Extract National ID fields
robovai-cli idcard --image path/to/id.jpg

# Start REST API & Web Control Dashboard
robovai-server --host 0.0.0.0 --port 8500

📡 REST API & WebSockets

Deploy as a standalone microservice:

robovai-server --port 8500

• Control Center Dashboard: http://localhost:8500/
• Interactive OpenAPI Documentation: http://localhost:8500/docs

🛠️ Architecture Overview

                               +-----------------------------+
                               |     RTSP Stream / Image     |
                               +--------------+--------------+
                                              |
                                              v
                               +--------------+--------------+
                               |    RoboVAI OCR Engine SDK   |
                               +--------------+--------------+
                                              |
            +---------------------------------+---------------------------------+
            |                                 |                                 |
            v                                 v
   +--------+--------+               +--------+--------+               +--------+--------+
   |   ALPREngine    |               |    IDEngine     |               |   FaceEngine    |
   | (YOLO + EasyOCR)|               | (3x YOLO Models)|               | (Face Match DB) |
   +--------+--------+               +--------+--------+               +--------+--------+
            |                                 |                                 |
            +---------------------------------+---------------------------------+
                                              |
                                              v
                               +--------------+--------------+
                               | FastAPI REST & WebSockets   |
                               +--------------+--------------+
                                              |
                                              v
                               +--------------+--------------+
                               | Smart Barrier Gate / Webhook|
                               +-----------------------------+

🤝 Contributing

We welcome contributions from the open-source community! Whether you are fixing bugs, improving docs, or proposing new features:

1. Fork the Repository on GitHub.
2. Create a Feature Branch: git checkout -b feature/amazing-feature
3. Commit Your Changes: git commit -m 'Add amazing feature'
4. Push to Branch: git push origin feature/amazing-feature
5. Open a Pull Request.

📜 License

This project is licensed under the MIT License.

👤 Author & Connect

Developed by Mohamed Shaban (محمد شعبان العتماني) — Founder & AI Architect at RoboVAI.

• ⭐ Star & Follow on GitHub: github.com/m0shaban
• 🌐 Personal Website: msalatmani.org
• 🏢 Company: robovai.tech
• 📦 PyPI Package: pypi.org/project/robovai-ocr/