Value Reader Computer Vision Dataset
964 Total Images
View All Images
Dataset Split
Train Set 92%
888Images
Valid Set 6%
58Images
Test Set 2%
18Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (black edges) in 256x96
Augmentations
Outputs per training example: 3
Rotation: Between -6° and +6°
Shear: ±7° Horizontal, ±7° Vertical
Grayscale: Apply to 10% of images
Hue: Between -20° and +20°
Noise: Up to 0.51% of pixels