This repository has been archived on 2026-02-15 . You can view files and clone it. You cannot open issues or pull requests or push a commit.
fa958d31f6234e5fcb8c4135a2e547d36809006b
New OCR method using classical Computer Vision: high-res rendering (432 DPI), deskew, dewarp, binarization, projection-profile layout analysis, multi-pass Tesseract OCR with region-specific PSM, and Y-coordinate line alignment. Includes bugfix for convert_pdf_to_image call (line 869) and 39 unit tests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Description
ARCHIVIERT - Migriert nach breakpilot-core, breakpilot-lehrer, breakpilot-compliance
Languages
TypeScript
47.5%
Python
34.1%
Go
12.5%
JavaScript
2.4%
HTML
1.3%
Other
1.9%