This repository has been archived on 2026-02-15.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.

BreakPilot Dev 2dd36099f1 feat(ocr): Add CV Document Reconstruction Pipeline for vocabulary extraction ...

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>

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

..

backend

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

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

docs

fix: Restore all files lost during destructive rebase

2026-02-09 09:51:32 +01:00

embedding-service

fix: Restore all files lost during destructive rebase

2026-02-09 09:51:32 +01:00

frontend

fix: Restore all files lost during destructive rebase

2026-02-09 09:51:32 +01:00

scripts

fix: Restore all files lost during destructive rebase

2026-02-09 09:51:32 +01:00

Dockerfile

fix: Restore all files lost during destructive rebase

2026-02-09 09:51:32 +01:00