Skip to content

GitLab

Switch branch/tag
  1. 10 Sep, 2024 2 commits
  3. 09 Sep, 2024 1 commit
    • myhloli's avatar
      feat(ocr): pass language parameter for custom model init · 4b372f3f
      myhloli authored 
      Pass the `lang` parameter to `custom_model_init` in `doc_analyze` to support language-specific OCR configurations. This enhancement allows the use of language information to improve OCR accuracy when processing PDFs.
      4b372f3f
  5. 03 Sep, 2024 1 commit
    • Xiaomeng Zhao's avatar
      refactor(pdf_extract_kit): implement singleton pattern for atomic models (#533) · aac91094
      Xiaomeng Zhao authored 
      Refactor the pdf_extract_kit module to utilize a singleton pattern when initializing
atomic models. This change ensures that atomic models are instantiated at most once,
optimizing memory usage and reducing redundant initialization steps. The AtomModelSingleton
class now manages the instantiation and retrieval of atomic models, improving the
overall structure and efficiency of the codebase.
      aac91094
  7. 02 Sep, 2024 1 commit
  9. 20 Aug, 2024 1 commit
    • Xiaomeng Zhao's avatar
      fix(pdf-extract): adjust box threshold for OCR detection (#447) · 041b9465
      Xiaomeng Zhao authored 
      Tuned the detection box threshold parameter in the OCR model initialization to improve the
accuracy of text extraction from images. The threshold was modified from 0.6 to
0.3 to filter out smaller detection boxes, which is expected to enhance the quality of the extracted
text by reducing noise and false positives in the OCR process.
      041b9465
  11. 09 Aug, 2024 2 commits
    • myhloli's avatar
      fix(pdf-extract-kit): ensure table extraction success with additional ending... · 334ccac2
      myhloli authored 
      fix(pdf-extract-kit): ensure table extraction success with additional ending conditionAdd an additional condition to determine the success of table extraction by checking
if the latex_code ends with 'end{table}'. This extends the validation to cover table
environments that may not strictly end with 'end{tabular}', thus improving the robustnessof table recognition processing.
      334ccac2
    • myhloli's avatar
      refactor(pdf_extract_kit): optimize image processing and table recognition... · 29e590a7
      myhloli authored 
      refactor(pdf_extract_kit): optimize image processing and table recognition logicRefactor the image processing logic for OCR and table recognition to ensure
consistency and improve performance. Remove redundant initialization of PIL images,
unify image cropping logic, and streamline the handling of formula detection results.
Also, adjust the table recognition process to improve integration with the updated image
processing logic and enhance overall efficiency.
      29e590a7
  13. 07 Aug, 2024 2 commits
  15. 05 Aug, 2024 1 commit
  17. 04 Aug, 2024 1 commit
    • myhloli's avatar
      fix(pdf-extract): ensure table recognition config defaults to disabled · 52156eae
      myhloli authored 
      If 'table-config' is not present in the configuration file, the table recognition
feature will default to being disabled to ensure consistent behavior. This change
adds a warning log and sets a default configuration for table recognition when the
expected config is missing.
      52156eae
  19. 02 Aug, 2024 1 commit
    • Kaiwen Liu's avatar
      feat(model inference): add table recognition and conversion to LaTeX (#284) · 37925f36
      Kaiwen Liu authored 
      * # add table recognition using struct-eqtable
## Changelog
31/07/20204
- Support table recognition. Table images will be converted into html.

### how to use the new feature:
set the attribute 'table-mode' to 'true' in magic-pdf.json

### caution:
it takes 200s to 500s to convert a single table image using cpu

* # add table recognition using struct-eqtable
## Changelog
31/07/20204
- Support table recognition. Table images will be converted into LaTex.

### how to use the new feature:
set the attribute 'table-mode' to 'true' in magic-pdf.json

### caution:
it takes 200s to 500s to convert a single table image using cpu

* # 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)。

* add table recognition and convertion to LaTeX

* add table recognition and conversion to LaTeX

* add table recognition and conversion to LaTeX

* add table recognition and conversion to LaTeX

---------
Co-authored-by: default avatarliukaiwen <liukaiwen@pjlab.org.cn>
      37925f36
  21. 01 Aug, 2024 3 commits
  23. 31 Jul, 2024 2 commits
    • liukaiwen's avatar
      # add table recognition using struct-eqtable · d6c58ecc
      liukaiwen authored 
      ## Changelog
31/07/20204
- Support table recognition. Table images will be converted into LaTex.

### how to use the new feature:
set the attribute 'table-mode' to 'true' in magic-pdf.json

### caution:
it takes 200s to 500s to convert a single table image using cpu
      d6c58ecc
    • liukaiwen's avatar
      # add table recognition using struct-eqtable · b29badc1
      liukaiwen authored 
      ## Changelog
31/07/20204
- Support table recognition. Table images will be converted into html.

### how to use the new feature:
set the attribute 'table-mode' to 'true' in magic-pdf.json

### caution:
it takes 200s to 500s to convert a single table image using cpu
      b29badc1
  25. 29 Jul, 2024 1 commit
  27. 28 Jul, 2024 1 commit
  29. 25 Jul, 2024 1 commit
  31. 24 Jul, 2024 3 commits
  33. 23 Jul, 2024 2 commits
  35. 22 Jul, 2024 2 commits
  37. 18 Jul, 2024 1 commit
  39. 12 Jul, 2024 5 commits
  41. 11 Jul, 2024 1 commit
  43. 10 Jul, 2024 2 commits
  45. 09 Jul, 2024 2 commits
  47. 08 Jul, 2024 1 commit
    • 赵小蒙's avatar
      update: · 1ee81a9a
      赵小蒙 authored 
      1.Disable scaling when loading large images.
2.Moving the logic for channel conversion in image processing.
      1ee81a9a