opensource/MinerU
3
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-09-24 23:10:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(table): improve table image processing

Browse Source 
- Replace np.array with np.asarray for better performance
- Add image color conversion from RGB to BGR using OpenCV
This commit is contained in:
myhloli
2024-11-05 16:10:19 +08:00
parent 376907ef22
commit 401dfa4e4f
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
magic_pdf/model/ppTableModel.py
+3 -1
View File
@@ -1,3 +1,4 @@
import cv2
from paddleocr.ppstructure.table.predict_table import TableSystem
from paddleocr.ppstructure.utility import init_args
from magic_pdf.libs.Constants import *
@@ -36,7 +37,8 @@ class ppTableModel(object):
- HTML (str): A string representing the HTML structure with content of the table.
"""
if isinstance(image, Image.Image):
image = np.array(image)
image = np.asarray(image)
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
pred_res, _ = self.table_sys(image)
pred_html = pred_res["html"]
# res = '<td><table border="1">' + pred_html.replace("<html><body><table>", "").replace(