Skip to content

GitLab

Unverified Commit 9675a574 authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #1088 from myhloli/dev 

feat(ocr): filter out low confidence ocr results
parents 61e88cb2 eb45a0e8
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 0 deletions
magic_pdf/model/sub_modules/ocr/paddleocr/ocr_utils.py
View file @ 9675a574
...@@ -214,6 +214,9 @@ def get_ocr_result_list(ocr_res, useful_list): ...@@ -214,6 +214,9 @@ def get_ocr_result_list(ocr_res, useful_list):
if len(box_ocr_res) == 2: if len(box_ocr_res) == 2:
p1, p2, p3, p4 = box_ocr_res[0] p1, p2, p3, p4 = box_ocr_res[0]
text, score = box_ocr_res[1] text, score = box_ocr_res[1]
# logger.info(f"text: {text}, score: {score}")
if score < 0.6: # 过滤低置信度的结果
continue
else: else:
p1, p2, p3, p4 = box_ocr_res p1, p2, p3, p4 = box_ocr_res
text, score = "", 1 text, score = "", 1
......
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