magic_pdf/pre_proc · 069bcfe656a1924c972a91649810c60dcd5ff758 · Qin Kaijie / pdf-miner

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
..
__init__.py		Loading commit data...
citationmarker_remove.py		Loading commit data...
construct_page_dict.py		Loading commit data...
cut_image.py		Loading commit data...
detect_equation.py		Loading commit data...
detect_footer_by_model.py		Loading commit data...
detect_footer_header_by_statistics.py		Loading commit data...
detect_footnote.py		Loading commit data...
detect_header.py		Loading commit data...
detect_images.py		Loading commit data...
detect_page_number.py		Loading commit data...
detect_tables.py		Loading commit data...
equations_replace.py		Loading commit data...
fix_image.py		Loading commit data...
fix_table.py		Loading commit data...
main_text_font.py		Loading commit data...
ocr_detect_all_bboxes.py		Loading commit data...
ocr_detect_layout.py		Loading commit data...
ocr_dict_merge.py		Loading commit data...
ocr_span_list_modify.py		Loading commit data...
pdf_pre_filter.py		Loading commit data...
post_layout_split.py		Loading commit data...
remove_bbox_overlap.py		Loading commit data...
remove_colored_strip_bbox.py		Loading commit data...
remove_footer_header.py		Loading commit data...
remove_rotate_bbox.py		Loading commit data...
resolve_bbox_conflict.py		Loading commit data...
solve_line_alien.py		Loading commit data...
statistics.py		Loading commit data...