Install Tesseract On Windows 10



Tesseract ocr for windows

Tesseract OCR is a very popular open source for recoginzing characters from images. In this tutorial, we will introduce how to install it and use it to extract text from images on windows 10. You can do like us by following our steps. Installing the Tesseract + Python “bindings” Let’s begin by getting pytesseract installed. To install pytesseract we’ll take advantage of pip. If you’re using a virtual environment (which I highly recommend so that you can separate different projects), use the workon command followed by the appropriate virtual environment name.

Tesseract Ocr Download Windows

Previously, I shared an article Making an Android OCR Application with Tesseract. This time, I’d like to share how to build the tesseract OCR library with Microsoft Visual Studio 2008 on Windows.

Building Tesseract

I’ve tried different ways to set up the building environment, and finally concluded that the most convenient way is to use the installer.

Download

32-bit
  • Windows installer of tesseract-ocr 3.02.02.

Installation

Follow the installation steps and check the option Tesseract development files:

Building

After finishing the installation, find the Visual Studio project folder:

Here are all relevant libraries that needed to be linked when building the OCR library.

Tesseract ocr for windows

In Visual Studio 2008, import and build the project. The outputs of DEBUG and RELEASE are respectively libtesseract302d.dll and libtesseract302.dll.

Tesseract ocr for windows

If you read the README file, please notice the paragraph:

Tesseract Ocr For Windows

Let’s take a further look at what Leptonica is.

Building Leptonica

liblept(Leptonica), written in C, is an open source library for image processing. It supports the file formats, including JPEG, PNG, TIFF, and GIF.

Install

Download

  • Source code, Visual Studio project, header files and relevant libraries:leptonica-1.68.

Building

Unpack all packages, and make the folder structure for building as following:

BuildFolderleptonica-1.68 contents:

In Visual Studio 2008, import and build the project. The outputs of DEBUG and RELEASE are respectively liblept168d.dll and liblept168.dll.

Tesseract Exe

References

Install Tesseract On Windows 10 64-bit

Leptonica
Leptonica & Visual Studio 2008
Tesseract-ocr