# feat(model inference): add table recognition and convertion to LaTeX

# What's Changed

### New Features

- Add table content recognition, we use weights of [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy) to convert table image to LaTex.

### Instruction

- pip install pypandoc struct-eqtable==0.1.0
- Download [StructEqTable weights](https://huggingface.co/wanderkid/PDF-Extract-Kit/tree/main/models/TabRec) and put it under models/ directory.
- Edit 'table-mode' value to turn on table recognition function which is turned off by default.
- If you did not download any models before, refer to [how to download models](docs/how_to_download_models_zh_cn.md)。

README_zh-CN_v2.md

@@ -91,6 +91,7 @@ MinerU诞生于[书生-浦语](https://github.com/InternLM/InternLM)的预训练
 - 保留原文档的结构，包括标题、段落、列表等
 - 提取图像、图片标题、表格、表格标题
 - 自动识别文档中的公式并将公式转换成latex
+- 自动识别文档中的表格并将表格转换成latex
 - 乱码PDF自动检测并启用OCR
 - 支持CPU和GPU环境
 - 支持windows/linux/mac平台
@@ -235,7 +236,7 @@ TODO
 - [ ] 正文中列表识别
 - [ ] 正文中代码块识别
 - [ ] 目录识别
-- [ ] 表格识别
+- [x] 表格识别
 - [ ] 化学式识别
 - [ ] 几何图形识别
 
@@ -270,6 +271,7 @@ The project currently leverages PyMuPDF to deliver advanced functionalities; how
 - [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
 - [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
 - [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
+- [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
 
 # Citation
 

docs/how_to_download_models_zh_cn.md

@@ -73,5 +73,15 @@ git clone https://www.modelscope.cn/wanderkid/PDF-Extract-Kit.git
 │       ├── README.md
 │       ├── tokenizer_config.json
 │       └── tokenizer.json
+│── TabRec
+│   └─StructEqTable
+│       ├── config.json
+│       ├── generation_config.json
+│       ├── model.safetensors
+│       ├── preprocessor_config.json
+│       ├── special_tokens_map.json
+│       ├── spiece.model
+│       ├── tokenizer.json
+│       └── tokenizer_config.json 
 └── README.md
 ```

magic_pdf/dict2md/ocr_mkcontent.py

@@ -253,9 +253,8 @@ def para_to_standard_format_v2(para_block, img_buket_path, page_idx):
         }
         for block in para_block['blocks']:
             if block['type'] == BlockType.TableBody:
-                #TODO
                 if block["lines"][0]["spans"][0].get('content', ''):
-                    para_content['table_body'] = f"\n {block['lines'][0]['spans'][0]['content']}  \n"
+                    para_content['table_body'] = f"\n\n$\n {block['lines'][0]['spans'][0]['content']}\n$\n\n"
                 para_content['img_path'] = join_path(img_buket_path, block["lines"][0]["spans"][0]['image_path'])
             if block['type'] == BlockType.TableCaption:
                 para_content['table_caption'] = merge_para_with_text(block)

magic_pdf/resources/model_config/model_configs.yaml

@@ -8,4 +8,4 @@ weights:
   layout: Layout/model_final.pth
   mfd: MFD/weights.pt
   mfr: MFR/UniMERNet
-  table: Table/
+  table: TabRec/StructEqTable
\ No newline at end of file

requirements-qa.txt

@@ -13,4 +13,5 @@ scikit-learn
 tqdm
 htmltabletomd
 pypandoc
-pyopenssl==24.0.0
+pyopenssl==24.0.0
\ No newline at end of file
+struct-eqtable==0.1.0
\ No newline at end of file

requirements.txt

@@ -8,4 +8,6 @@ fast-langdetect==0.2.0
 wordninja>=2.0.0
 scikit-learn>=1.0.2
 pdfminer.six==20231228
+pypandoc
+struct-eqtable==0.1.0
 # The requirements.txt must ensure that only necessary external dependencies are introduced. If there are new dependencies to add, please contact the project administrator.