Need help with ocrtable?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

181 Stars 55 Forks MIT License 34 Commits 6 Opened issues


Recognize tables and text from scanned images that contain tables. 从包含表格的扫描图片中识别表格和文字

Services available


Need anything else?

Contributors list

No Data

OCR Table



For scanning copies containing tables or forms, many OCR softwares recognize text in entire page as whole by discarding all tables. Sometimes it is inconvenient for users. This project retains table structures as well and save the recognizing result as a Microsoft Word document.

This project consists of a DLL and an EXE, both of which are 64-bit. The subdirectory corresponding to DLL is tableocr, developed by Visual C++. It implements core functions, including table structure recognition and text recognition. the subdirectory corresponding to EXE is ocrtable, developed by C#, which provides user interface. Below the pictures directory are sample scanning copies.

Suggestions are welcome. In addition to submitting an issue, you can email me as well. My email address is 31416\

Recognition Performance

Download pre-compiled components

English Character Recognition Example

Please do not select "Recognize simplified Chinese characters".

Scanning copy:

Result (Note that tables are not displayed in order):

Chinese Character Recognition Example

You need select "Recognize simplified Chinese characters".

Scanning copy:


Chinese character recognition relies on Tesseract official pre-training package, which supports only a few fonts. Users can consider training Tesseract mannually or using other OCR technologies instead.

Development Environment

DLL Development environment

Windows 7 SP1 x64

Visual Studio Community 2017

OpenCV 3.4.3

Tesseract 4.0.0-beta.4 (Compiled by Git source. Please search online resources to learn how to setup Chinese character recognition.)

For the convenience of debugging, the DLL module includes Debug EXE configuration, which outputs EXE. The program displays table structures and outputs recognized text by OutputDebugString Windows API. Note that recognition process may take long time, and the popup window needs to be closed by keyboard instead of mouse.

EXE Development environment

Windows 7 SP1 x64

Visual Studio Community 2017

DocX(Xceed.Words.NET.dll)(downloaded by nuget)

Revision History


  1. Complete the first edition.


  1. Fix bugs in DLL.

  2. Add international support in EXE.

  3. Update this document.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.