Table 3 Key dataset statistics.

From: Attention based unified architecture for Arabic text detection on traffic panels to advance autonomous navigation in natural scenes

Attribute

Description

Total Images

Approximately 10,000 images, evenly distributed across three categories.

Resolution

Images are standardized to 224 × 224 pixels for consistent model training.

Annotation Format

Pascal VOC XML format is used for image annotations.

Text Variability

The dataset exhibits diverse styles, stroke thicknesses, and symbol shapes.

Back to article page