Multi-Texture Sheet Music Recognition Benchmark

SMB is a benchmark dataset of printed Common Western Modern Notation scores developed by the Pattern Recognition and Artificial Intelligence Group at the University of Alicante. It is designed for Optical Music Recognition and image segmentation tasks involving full-page music scores.

Use Cases

• Train Optical Music Recognition systems on full-page sheet music images for system-level evaluation.
• Segment music regions within multi-texture page images for layout analysis.
• Benchmark computer vision models on the specific domain of printed music notation.

Strengths

• Dataset is explicitly designed as a benchmark for Optical Music Recognition.
• Focuses on the specific domain of printed Common Western Modern Notation.

Limitations

• Dataset size, row count, and specific file formats are unknown.
• Sample data and column structure are unavailable for inspection.

Provenance

Source

Pattern Recognition and Artificial Intelligence Group (PRAIG) at the University of Alicante

Collection Method

Developed as a dataset of printed Common Western Modern Notation scores.

Time Range

null

Freshness

null

Geography

null