pdf 图表检测不准确 #14174
Unanswered
qihanghou726
asked this question in
Q&A
pdf 图表检测不准确
#14174
Replies: 1 comment 1 reply
-
dataset_1.pdf |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
🔎 Search before asking
🐛 Bug (问题描述)
使用版面分析模型时出现的问题
在使用版面分析模型默认参数时出现表格检测不完整
在使用lang="en "参数后出现表格图片识别错误
在使用layout_model_dir="picodet_lcnet_x1_0_fgd_layout_infer"参数时虽然解决了上面表格的问题,但是pdf其他地方的很多图片都被检测为表格
🏃♂️ Environment (运行环境)
ubuntu 18.04
python 3.9.19
🌰 Minimal Reproducible Example (最小可复现问题的Demo)
ocr_engine = PPStructure(show_log=True)
img_path="xxx"
result = ocr_engine(cv2.imread(img_path))
save_structure_res(result, save_folder+f'/ocr_result',os.path.basename(img_path).split('.')[0])
Beta Was this translation helpful? Give feedback.
All reactions