YOLOCarAndPlateDetection: Fine-Tuned YOLOv8 for Car & License Plate Detection

YOLOCarAndPlateDetection is a deep learning model fine-tuned from YOLOv8 (Ultralytics) to detect and localize cars and license plates in real-world traffic images.
It demonstrates a complete object detection workflow, from dataset annotation and model training to deployment on Streamlit and Hugging Face Spaces for real-time inference.

⚠️ Disclaimer: This model is designed for research, educational, and demonstration purposes only.
It should not be used in production or surveillance systems without additional validation and ethical review.

---

Model Details

Key Features:

• Dual-class detection for vehicles and license plates
• Fine-tuned from YOLOv8 pretrained weights (trained on the COCO dataset)
• High-accuracy object detection with bounding boxes and confidence scores
• Real-time performance suitable for deployment in traffic monitoring systems
• Streamlit-based interactive app for user-friendly inference

Skills & Technologies Used:

• Ultralytics YOLOv8 for object detection
• PyTorch backend for model training and inference
• OpenCV for image preprocessing and visualization
• Streamlit & Hugging Face Spaces for deployment
• Transfer learning on a custom annotated dataset

---

• Developed by: Rawan Alwadeya
• Model type: Object Detection (YOLOv8)
• Language(s): N/A (Image model)
• License: MIT

---

Uses

This model can be applied to:

• Smart parking systems for vehicle and plate identification
• Traffic monitoring and automation
• AI-assisted law enforcement tools
• Research and education in computer vision and deep learning

---

Performance

The fine-tuned YOLOv8 model achieved the following results on the test dataset:

• Precision: 90%
• Recall: 89%
• mAP@50: 91%

These metrics demonstrate robust detection accuracy and generalization across different lighting, angles, and vehicle types.

---

Deployment

• Hugging Face Repo: YOLOCarAndPlateDetection
• Demo Video: View on LinkedIn

Users can upload traffic images to view bounding boxes for detected vehicles and license plates in real time, making it ideal for smart city applications and AI-driven automation.

---

👩‍💻 Author

Rawan Alwadeya
AI Engineer | Generative AI Engineer | Data Scientist

• 📧 Email: [email protected]
• 🌐 LinkedIn Profile

---

Example Usage

from ultralytics import YOLO
import cv2

# Load model from Hugging Face Hub
model = YOLO("RawanAlwadeya/YOLOCarAndPlateDetection")

# Run inference on an example image
results = model("car_and_plate_example.jpg")

# Visualize results
for r in results:
    im_array = r.plot()  # BGR image with predictions
    cv2.imshow("Car & Plate Detection", im_array)
    cv2.waitKey(0)
    cv2.destroyAllWindows()