Blueprint OCR Dataset in YOLO Format for Object Detection

Packshotter's Blueprint OCR Dataset provides annotated images of blueprints formatted for YOLO object detection models. Images have been resized to 50% resolution to facilitate faster training and reduce download size. The dataset was last updated on January 14, 2026.

Use Cases

• Train YOLO-based object detection models based on the provided YOLO format annotations.
• Develop Optical Character Recognition (OCR) systems for technical documents based on the blueprint images.
• Benchmark model performance on a domain-specific image dataset based on the blueprint content.
• Fine-tune pre-trained vision models for specialized blueprint analysis tasks.

Strengths

• Images are pre-processed to 50% resolution, which likely reduces training time and storage requirements.
• Annotations are provided in YOLO format, a standard for object detection tasks.

Limitations

• Description metadata is limited; actual data quality, annotation accuracy, and class definitions require manual inspection after download.
• Row count and dataset scale are unknown, which may limit suitability assessment for large-scale projects.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

packshotter on Hugging Face.

Freshness

Last updated 2026-01-14 14:26:35; freshness should be verified.