feat(ocr): Add CV Document Reconstruction Pipeline for vocabulary extraction

Browse Source

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>

...

This commit is contained in:

BreakPilot Dev

2026-02-09 23:52:35 +01:00

parent 916ecef476

commit fa958d31f6

4 changed files with 2096 additions and 50 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1019

klausur-service/backend/cv_vocab_pipeline.py Normal file

File diff suppressed because it is too large Load Diff