Glasses Detection Yolo Format

Explore our carefully selected dataset designed for object detection using the YOLO framework. This dataset focuses on distinguishing between people wearing glasses and those who aren’t.

Dataset Overview:

Our dataset includes high-quality images gathered responsibly through the Unsplash API. This ensures that our dataset reflects real-life situations, making it perfect for facial recognition and accessory detection technologies.

Key Features:

• Wide Range of Images: We have a good mix of people with and without glasses, covering various facial features and styles.
• Accurate Annotations: Each image is labeled with precision using advanced tools, ensuring reliable results for YOLO-based object detection models.
  1. x_center: Normalized center x-coordinate of the bounding box.
  2. y_center: Normalized center y-coordinate of the bounding box.
  3. width: Normalized width of the bounding box.
  4. height: Normalized height of the bounding box.

  Coordinates are normalized by dividing by image width and height. Annotations are saved in a .txt file with each image, following the pattern: class_id x_center y_center width height.

Utilization:

You can use our dataset to improve your computer vision models, enhance accessory detection algorithms, or conduct research in optical recognition technologies.

This dataset is sourced from Kaggle.