Benjamin Admin 8ad5823fd8 feat(ocr-pipeline): word-center grid with section-break detection
Replace rigid uniform grid with bottom-up approach that derives row
boundaries from word vertical centers:
- Group words into line clusters, compute center_y per cluster
- Compute pitch (distance between consecutive centers)
- Detect section breaks where gap > 1.8× median pitch
- Place row boundaries at midpoints between consecutive centers
- Per-section local pitch adapts to heading/paragraph spacing
- Validate ≥85% word placement, fallback to gap-based rows

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-01 12:04:08 +01:00
Description
No description provided
42 MiB
Languages
TypeScript 60.2%
Python 32.9%
Go 5.5%
C# 0.8%
CSS 0.2%
Other 0.3%