Complete installation and use of TESSERACT-OCR



In the image of interest in the processing of text recognition, the individual found that some of the tutorials are incomplete. Need to find the west to put together. So this comb the next Windows installation complete record, in the application is the use of Python programming.

First of all, the prerequisite downloads related packages.

Includes Windows Installer (tesseract-ocr-setup-3.05.01) with TESSERACT-OCR, Pillow, Pytesseract. There is also the TESSERACT-OCR Chinese font chi_sim.trainedata,eng.trainedata.

Then install them in the following order.

1, first installs the TESSERACT-OCR Windows installs the edition.

Directly perform the download good Tesseract-ocr-setup-3.05.01.exe, the next installation can be.

1.1 In the system variable path of the environment variable, add the TESSERACT-OCR installation path (such as C:\Program Files (x86) \TESSERACT-OCR;). Note that when you add a start, use ";" Separated from the previous variable, ending with ";" End.

1.2 In the system variable of the environment variable, add a tessdata_prefix variable name, variable value or TESSERACT-OCR installation path (such as C:\Program Files (x86) \TESSERACT-OCR;)

1.3 Copy the Chinese font of the downloaded TESSERACT-OCR to the TESSERACT-OCR installation directory (such as C:\Program Files (x86) \TESSERACT-OCR;) Tessdata directory.

1.4 Verify that the installation is successful

Enter the cmd window, typing the command CD C:\Program Files (x86) \TESSERACT-OCR, in the typing tesseract, the following information should indicate that the installation was successful.

You can also use the command tesseract--list-langs to view the TESSERACT-OCR support language.

2, and then install pillow.

Pip Install pillow or pythonsetup.py install (download source)

3, and then install Pytesseract.

Pip install Pytesseract or pythonsetup.py install (download source)