HR Beta

Signature Comparator

Classification

Signature Comparator Image Dataset

v1

Semi-Full Version

Generated on Mar 6, 2024

Dataset Split

Train Set 88%
5544Images
Valid Set 8%
528Images
Test Set 4%
264Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Noise: Up to 0.1% of pixels