Model Card for YOLOEgyptianCurrencyDetection: Fine-Tuned YOLOv8 for Currency Recognition

YOLOEgyptianCurrencyDetection is a deep learning model built upon YOLOv8 (Ultralytics) and fine-tuned to detect and classify Egyptian banknotes across different denominations in real time.
The project demonstrates how transfer learning can adapt a general-purpose object detection model (trained on COCO) to a specialized domain like financial technology and currency recognition.

⚠️ Disclaimer: This model is intended for research, educational, and demonstration purposes only. It should not be used in production or financial systems without further validation and regulatory compliance.

---

Model Details

Key Features:

• Object detection and classification for Egyptian currency denominations
• Fine-tuned from YOLOv8 pretrained weights (COCO dataset)
• Real-time inference with bounding boxes and labels
• Supports detection of multiple notes in a single frame
• Automatically calculates total currency value in the Streamlit app

Skills & Technologies Used:

• Ultralytics YOLOv8 for object detection
• Transfer learning on a custom Egyptian currency dataset
• PyTorch backend with GPU acceleration
• Streamlit for interactive deployment
• Hugging Face Spaces for public hosting

---

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

---

Uses

This model can be applied to:

• Automated payment systems and currency counting machines
• Financial verification tools and cash-handling automation
• Research in AI-based object detection and computer vision
• Educational projects demonstrating transfer learning and real-time detection

---

Performance

The fine-tuned model achieved excellent results on the test set:

• Precision: 99.6%
• Recall: 100%
• mAP@50: 99.5%
• mAP@50-95: 96.5%

These metrics confirm the model’s accuracy, robustness, and real-time detection capability, even under varying lighting and background conditions.

---

Deployment

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

Users can upload images of Egyptian banknotes and instantly view:

• Bounding boxes and denomination labels
• Automatic total value calculation

---

👩‍💻 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/YOLOEgyptianCurrencyDetection")

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

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