---
title: Jordanian LPR - Vehicle Plate Detection and Recognition. (نظام التعرف على لوحات المركبات الأردنية)
emoji: 🚘
colorFrom: green
colorTo: gray
sdk: gradio
sdk_version: 6.19.0
python_version: '3.13'
app_file: app.py
pinned: false
license: mit
short_description: Detecting and recognizing Jordanian vehicle license plates.
tags:
- object-detection
- yolov26
- Vechicles
- edge-ai
- traffic violation
- Jordan
- Jordan License Plate Recognition
- LPTR
- computer-vision
- jordan
---
# 🚘 Jordanian LPR - Vehicle Plate Detection and Recognition.
> نظام آلي للكشف عن لوحات ترخيص المركبات الأردنية والتعرف عليها باستخدام رؤية الحاسوب والتعلم العميق.
---
## Overview
An automated system for detecting and recognizing Jordanian vehicle license plates using computer vision and deep learning. The model handles multiple plate types under varied real-world conditions including daylight, night, and motion blur.
## Supported Plate Types
Jordanian vehicle license plates are divided into two primary sections, each serving a distinct identification purpose. The left side of the plate contains the vehicle classification and registration category information, which identifies the type of vehicle and its registration class within the Kingdom. Depending on the plate type, this section may include indicators for private vehicles, public transportation, government vehicles, diplomatic vehicles, or other designated categories. The right side of the plate contains the unique vehicle registration number, which serves as the primary identifier for the individual vehicle. This number is unique within its respective classification and is used by authorities and automated recognition systems to distinguish one vehicle from another. Together, these two sections provide both the classification context and the unique identification necessary for vehicle registration, law enforcement, and automated license plate recognition (ALPR) systems.
| Type | Background| Text | Samele
|-------------|-----------|-------| ----------------------------------------
| Private | White | Black | |
| Government | Red | White | |
| Taxi | Green | White | |
| Diplomatic | Blue | White | |
| Temporary | Yellow | Black | |
| Rental | Green | Yellow | |
---
**Detections**:
The current license plate recognition model is still under active development and continuous improvement. As a result, the recognition accuracy for certain plate categories may not yet meet the desired performance levels and should be considered preliminary. The model has been primarily trained and optimized for the most common plate types, and therefore the highest recognition accuracy in this release is achieved for private, government, and taxi license plates. Additional training data, validation, and model enhancements are ongoing to improve the detection and recognition performance across all remaining plate categories in future versions.
| Type | Code | Samele
|-------------|------|-----------------------|
| Private |JO-PVT| JO-PVT 46-93402 |
| Government |JO-GOV| JO-GOV 1-1342 |
| Taxi |JO-TXI| JO-TXI 22-75940 |
| Temporary |JO-TMP| Under Development |
| Rental |JO-RNT| Under Development |
**Demo video** (4k 29s):
## Pipeline
```
Input image → Vehicle Detection → Plate detection → Crop & align → Trained Plate Number Recognition / Plate Patterns recognition → Plate Number output
```
---
## Model Architecture
| Component | Details |
|----------------------|----------------------|
| Vechile Detection | YOLOv26 |
| Plate Detection | Fine Tuned Model |
| Platge Recognition | Fine Tuned Model |
| Framework | CV2/PyTorch |
| Input size | 640 × 640 |
---
## Dataset
| Property | Details |
|--------------|----------------------|
| Total images | 50 000 Plate |
| Split | 80 / 10 / 10 |
| Conditions | Day, blur |
| Annotation | Bounding box + text |
---
## Limitations
- Performance degrades in heavy rain, fog, or extreme low light
- Heavily occluded or damaged plates may not be recognized
- Not trained on non-Jordanian plates — unreliable on foreign vehicles
- Arabic numeral OCR accuracy may vary on older or worn plates
---
## Intended Use
✅ Parking management systems
✅ Traffic monitoring
✅ Access control
✅ Toll systems
❌ Mass surveillance
❌ Unauthorized tracking
---
## Run locally
```bash
pip install -r requirements.txt
python app.py
```
Weights ship in this repo (`raccoon-yolov8n-v1.4.onnx`, MIT licensed), or set
`MODEL_PATH` to your own export.
## Links
- Source code: https://huggingface.co/spaces/digitalbigbrain/test
- Built by [@DigitalBigBrain](https://www.DigitalBigBrain.com) for the Gradio Build Small hackathon, Mobility AI
## Citation
```bibtex
@misc{jordanian-lpr,
title = {Jordanian LPR: Vehicle Plate Detection and Recognition},
author = {digitalbigbrain},
year = {2026},
url = {https://huggingface.co/spaces/digitalbigbrain/test}
}
```
---
## License
MIT License — see `LICENSE` for details.
|
| Government | Red | White | 
|
| Taxi | Green | White | 
|
| Diplomatic | Blue | White | 
|
| Temporary | Yellow | Black | 
|
| Rental | Green | Yellow | 
|
---
**Detections**:
The current license plate recognition model is still under active development and continuous improvement. As a result, the recognition accuracy for certain plate categories may not yet meet the desired performance levels and should be considered preliminary. The model has been primarily trained and optimized for the most common plate types, and therefore the highest recognition accuracy in this release is achieved for private, government, and taxi license plates. Additional training data, validation, and model enhancements are ongoing to improve the detection and recognition performance across all remaining plate categories in future versions.
| Type | Code | Samele
|-------------|------|-----------------------|
| Private |JO-PVT| JO-PVT 46-93402 |
| Government |JO-GOV| JO-GOV 1-1342 |
| Taxi |JO-TXI| JO-TXI 22-75940 |
| Temporary |JO-TMP| Under Development |
| Rental |JO-RNT| Under Development |
**Demo video** (4k 29s):
## Pipeline
```
Input image → Vehicle Detection → Plate detection → Crop & align → Trained Plate Number Recognition / Plate Patterns recognition → Plate Number output
```
---
## Model Architecture
| Component | Details |
|----------------------|----------------------|
| Vechile Detection | YOLOv26 |
| Plate Detection | Fine Tuned Model |
| Platge Recognition | Fine Tuned Model |
| Framework | CV2/PyTorch |
| Input size | 640 × 640 |
---
## Dataset
| Property | Details |
|--------------|----------------------|
| Total images | 50 000 Plate |
| Split | 80 / 10 / 10 |
| Conditions | Day, blur |
| Annotation | Bounding box + text |
---
## Limitations
- Performance degrades in heavy rain, fog, or extreme low light
- Heavily occluded or damaged plates may not be recognized
- Not trained on non-Jordanian plates — unreliable on foreign vehicles
- Arabic numeral OCR accuracy may vary on older or worn plates
---
## Intended Use
✅ Parking management systems
✅ Traffic monitoring
✅ Access control
✅ Toll systems
❌ Mass surveillance
❌ Unauthorized tracking
---
## Run locally
```bash
pip install -r requirements.txt
python app.py
```
Weights ship in this repo (`raccoon-yolov8n-v1.4.onnx`, MIT licensed), or set
`MODEL_PATH` to your own export.
## Links
- Source code: https://huggingface.co/spaces/digitalbigbrain/test
- Built by [@DigitalBigBrain](https://www.DigitalBigBrain.com) for the Gradio Build Small hackathon, Mobility AI
## Citation
```bibtex
@misc{jordanian-lpr,
title = {Jordanian LPR: Vehicle Plate Detection and Recognition},
author = {digitalbigbrain},
year = {2026},
url = {https://huggingface.co/spaces/digitalbigbrain/test}
}
```
---
## License
MIT License — see `LICENSE` for details.