Yolov8n Handwritten Text Detection

🚀 YOLOv8 Handwritten Text Detection

YOLOv8 is optimized for handwritten text detection, offering high - speed and accurate object detection for real - time applications.

🚀 Quick Start

This section provides a guide on how to quickly start using the YOLOv8 handwritten text detection model.

✨ Features

• High - performance Algorithm: YOLOv8 is the latest version of the YOLO object detection algorithm, known for its excellent speed and accuracy, suitable for real - time applications.
• Specificity for Handwritten Texts: The model has been fine - tuned on a diverse handwritten text dataset, enhancing its ability to detect handwritten content compared to typed or printed materials.

📦 Installation

To use this model, you need to install the ultralytics library. You can install it using the following command:

pip install ultralytics

💻 Usage Examples

Basic Usage

The following code demonstrates how to load the model, perform predictions, and visualize the results:

from ultralytics import YOLO
from huggingface_hub import hf_hub_download
from matplotlib import pyplot as plt

# Load the weights from our repository
model_path = hf_hub_download(local_dir=".",
                             repo_id="armvectores/yolov8n_handwritten_text_detection",
                             filename="best.pt")
model = YOLO(model_path)

# Load test blank
test_blank_path = hf_hub_download(local_dir=".",
                             repo_id="armvectores/yolov8n_handwritten_text_detection",
                             filename="test_blank.png")

# Do the predictions
res = model.predict(source=test_blank_path, project='.',name='detected', exist_ok=True, save=True, show=False, show_labels=False, show_conf=False, conf=0.5, )

plt.figure(figsize=(15,10))
plt.imshow(plt.imread('detected/test_blank.png'))
plt.show()

📚 Documentation

Tests

The following are some test results:

Metrics

The final Intersection over Union (IoU) is 0.98. The IoU during training is shown in the following image: