Skip to content

GitLab

"docs/developer_guide/setup_github_runner.md" did not exist on "4f723edd3baf3823eddfb9d6426548daba17c687"
Commit 90ea9096 authored by 赵小蒙's avatar 赵小蒙
Browse files

部分layout最底部的文本圈不全，降低阈值减少底边文本被丢弃的可能性

parent 0dbbf9c3
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
magic_pdf/pre_proc/ocr_dict_merge.py
View file @ 90ea9096
...@@ -66,7 +66,7 @@ def merge_spans_to_line_by_layout(spans, layout_bboxes): ...@@ -66,7 +66,7 @@ def merge_spans_to_line_by_layout(spans, layout_bboxes):
# 遍历spans,将每个span放入对应的layout中 # 遍历spans,将每个span放入对应的layout中
layout_sapns = [] layout_sapns = []
for span in spans: for span in spans:
if calculate_overlap_area_in_bbox1_area_ratio(span['bbox'], layout_bbox) > 0.65: if calculate_overlap_area_in_bbox1_area_ratio(span['bbox'], layout_bbox) > 0.6:
layout_sapns.append(span) layout_sapns.append(span)
# 如果layout_sapns不为空，则放入new_spans中 # 如果layout_sapns不为空，则放入new_spans中
if len(layout_sapns) > 0: if len(layout_sapns) > 0:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment