PyPI

简介

lineless_table_rec库源于阿里读光-LORE无线表格结构识别模型。

在这里，我们做的工作主要包括以下两点：

  1. 将模型转换为ONNX格式，便于部署
  2. 完善后处理代码，与OCR识别模型整合，可以保证输出结果为完整的表格和对应的内容

模型转换ONNX

详情参考：ConvertLOREToONNX

安装 

  pip install lineless_table_rec

使用 

  import os

from lineless_table_rec import LinelessTableRecognition
from lineless_table_rec.utils_table_recover import (
    format_html,
    plot_rec_box,
    plot_rec_box_with_logic_info,
)

output_dir = "outputs"
img_path = "tests/test_files/lineless_table_recognition.jpg"
table_rec = LinelessTableRecognition()

html, elasp, polygons, logic_points, ocr_res = table_rec(img_path)
print(f"cost: {elasp:.5f}")

complete_html = format_html(html)
os.makedirs(os.path.dirname(f"{output_dir}/table.html"), exist_ok=True)

with open(f"{output_dir}/table.html", "w", encoding="utf-8") as file:
    file.write(complete_html)

plot_rec_box_with_logic_info(
    img_path, f"{output_dir}/table_rec_box.jpg", logic_points, polygons
)
plot_rec_box(img_path, f"{output_dir}/ocr_box.jpg", ocr_res)
  
  $ lineless_table_rec -img tests/test_files/lineless_table_recognition.jpg

查看效果

识别结果（点击展开） 
  <html>
<body>
    <table>
        <tbody>
            <tr>
                <td rowspan="1" colspan="1">姓名</td>
                <td rowspan="1" colspan="1">年龄</td>
                <td rowspan="1" colspan="1">性别</td>
                <td rowspan="1" colspan="1">身高/m</td>
                <td rowspan="1" colspan="1">体重/kg</td>
                <td rowspan="1" colspan="1">BMI/(kg/m²)</td>
            </tr>
            <tr>
                <td rowspan="1" colspan="1">Duke</td>
                <td rowspan="1" colspan="1">34</td>
                <td rowspan="1" colspan="1">男</td>
                <td rowspan="1" colspan="1">1.74</td>
                <td rowspan="1" colspan="1">70</td>
                <td rowspan="1" colspan="1">23</td>
            </tr>
            <tr>
                <td rowspan="1" colspan="1">Ella</td>
                <td rowspan="1" colspan="1">26</td>
                <td rowspan="1" colspan="1">女</td>
                <td rowspan="1" colspan="1">1.60</td>
                <td rowspan="1" colspan="1">58</td>
                <td rowspan="1" colspan="1">23</td>
            </tr>
            <tr>
                <td rowspan="1" colspan="1">Eartha</td>
                <td rowspan="1" colspan="1"></td>
                <td rowspan="1" colspan="1">女</td>
                <td rowspan="1" colspan="1">1.34</td>
                <td rowspan="1" colspan="1">29</td>
                <td rowspan="1" colspan="1">16</td>
            </tr>
            <tr>
                <td rowspan="1" colspan="1">Thelonious</td>
                <td rowspan="1" colspan="1">6</td>
                <td rowspan="1" colspan="1">男</td>
                <td rowspan="1" colspan="1">1.07</td>
                <td rowspan="1" colspan="1">17</td>
                <td rowspan="1" colspan="1">15</td>
            </tr>
            <tr>
                <td rowspan="1" colspan="1">TARO</td>
                <td rowspan="1" colspan="1">22</td>
                <td rowspan="1" colspan="1">男</td>
                <td rowspan="1" colspan="1">1.728</td>
                <td rowspan="1" colspan="1">65</td>
                <td rowspan="1" colspan="1">21.7</td>
            </tr>
            <tr>
                <td rowspan="1" colspan="1">HANAKO</td>
                <td rowspan="1" colspan="1">22</td>
                <td rowspan="1" colspan="1">女</td>
                <td rowspan="1" colspan="1">1.60</td>
                <td rowspan="1" colspan="1">53</td>
                <td rowspan="1" colspan="1">20.7</td>
            </tr>
            <tr>
                <td rowspan="1" colspan="1">NARMAN</td>
                <td rowspan="1" colspan="1">38</td>
                <td rowspan="1" colspan="1">男</td>
                <td rowspan="1" colspan="1">1.76</td>
                <td rowspan="1" colspan="1">73</td>
                <td rowspan="1" colspan="1"></td>
            </tr>
            <tr>
                <td rowspan="1" colspan="1">NAOMI</td>
                <td rowspan="1" colspan="1">23</td>
                <td rowspan="1" colspan="1">女</td>
                <td rowspan="1" colspan="1">1.63</td>
                <td rowspan="1" colspan="1">60</td>
                <td rowspan="1" colspan="1"></td>
            </tr>
        </tbody>
    </table>
</body>

</html>
Edit this page

Last updated 12 Sep 2024, 19:30 +0800 . history