Files · 1807126e7fc97086cbaa96f171ea1ea3fae23937 · Qin Kaijie / pdf-miner · GitLab

History Find file

refactor(ocr): adjust OCR processing parameters · 1807126e

myhloli authored Oct 25, 2024

- Lower the Y-axis overlap threshold for merging spans into lines from0.6 to 0.5
- Reduce the unclip ratio for OCR detection from 2.4 to 1.8

1807126e

Name	Last commit	Last update
.github		Loading commit data...
demo		Loading commit data...
docs		Loading commit data...
magic_pdf		Loading commit data...
old_docs		Loading commit data...
projects		Loading commit data...
signatures/version1		Loading commit data...
tests		Loading commit data...
.gitignore		Loading commit data...
.pre-commit-config.yaml		Loading commit data...
.readthedocs.yaml		Loading commit data...
Dockerfile		Loading commit data...
LICENSE.md		Loading commit data...
MinerU_CLA.md		Loading commit data...
README.md		Loading commit data...
README_ja-JP.md		Loading commit data...
README_zh-CN.md		Loading commit data...
magic-pdf.template.json		Loading commit data...
requirements-docker.txt		Loading commit data...
requirements-qa.txt		Loading commit data...
requirements.txt		Loading commit data...
setup.py		Loading commit data...
update_version.py		Loading commit data...