Tesseract OCR

https://tesseract-ocr.github.io/tessdoc/
Admin
Tesseract OCR is an open-source optical character recognition engine that extracts printed text from...
Tokens:81,431
Snippets:634
Trust Score:9.7
Update:1 month ago
Show doc for...
Tokens:
Raw
### Build and install Tesseract

Source: https://tesseract-ocr.github.io/tessdoc/Compiling-%E2%80%93-GitInstallation.html

Standard sequence of commands to configure, build, and install Tesseract from source.

```bash
    cd tesseract
    ./autogen.sh
    ./configure
    make
    sudo make install
    sudo ldconfig
```

--------------------------------

### Install Tesseract Developer Tools

Source: https://tesseract-ocr.github.io/tessdoc/Compiling

Command to install development headers required for training tools.

```bash
sudo apt install libtesseract-dev
```

--------------------------------

### Install Pango for training tools

Source: https://tesseract-ocr.github.io/tessdoc/Compiling-%E2%80%93-GitInstallation.html

Install Pango development headers required if building Tesseract training tools.

```bash
apt-get install libpango1.0-dev
```

--------------------------------

### Build and install Tesseract with training tools

Source: https://tesseract-ocr.github.io/tessdoc/Compiling-%E2%80%93-GitInstallation.html

Sequence of commands to build and install Tesseract including the training tools.

```bash
    cd tesseract
    ./autogen.sh
    ./configure
    make
    sudo make install
    sudo ldconfig
    make training
    sudo make training-install
```

--------------------------------

### Build and install Tesseract from command line

Source: https://tesseract-ocr.github.io/tessdoc/Compiling

Command to build the Release configuration and install Tesseract to the default location.

```bash
cmake --build . --config Release --target install

```

--------------------------------

### Install Tesseract via Snap

Source: https://tesseract-ocr.github.io/tessdoc/Installation.html

Install the Tesseract binary using snapd on supported distributions.

```bash
sudo snap install --channel=edge tesseract
```

--------------------------------

### Install Tesseract on Ubuntu

Source: https://tesseract-ocr.github.io/tessdoc/Installation.html

Use apt to install Tesseract and its developer tools on Ubuntu systems.

```bash
sudo apt install tesseract-ocr
sudo apt install libtesseract-dev
```

--------------------------------

### Build and install training tools

Source: https://tesseract-ocr.github.io/tessdoc/tess5/TrainingTesseract-5.html

Commands to build and install the training tools after configuring Tesseract. Requires optional dependencies to be available.

```bash
make
make training
sudo make training-install
```

--------------------------------

### Install Tesseract on CentOS_8_Stream

Source: https://tesseract-ocr.github.io/tessdoc/InstallationOpenSuse.html

Adds the openSUSE repository, imports the GPG key, and installs Tesseract with all language packs. Run as root.

```bash
sudo dnf config-manager --add-repo https://download.opensuse.org/repositories/home:/Alexander_Pozdnyakov/CentOS_8_Stream/
sudo rpm --import https://build.opensuse.org/projects/home:Alexander_Pozdnyakov/signing_keys/download?kind=gpg
sudo dnf install tesseract
sudo dnf install tesseract-langpack-*

```

--------------------------------

### Install optional manpage dependencies

Source: https://tesseract-ocr.github.io/tessdoc/Compiling-%E2%80%93-GitInstallation.html

Install asciidoc and related tools to build optional manpages.

```bash
apt-get install --no-install-recommends asciidoc docbook-xsl xsltproc
```

--------------------------------

### Example build error output

Source: https://tesseract-ocr.github.io/tessdoc/Compiling-%E2%80%93-GitInstallation.html

Example of a common build error encountered during the make process.

```text
make  all-recursive
Making all in ccstruct
/bin/sh ../libtool --tag=CXX   --mode=compile g++ -DHAVE_CONFIG_H -I. -
I..  -I../ccutil -I../cutil -I../image -I../viewer -I/opt/local/
include -I/usr/local/include/leptonica  -g -O2 -MT blobbox.lo -MD -MP -
MF .deps/blobbox.Tpo -c -o blobbox.lo blobbox.cpp
mv -f .deps/blobbox.Tpo .deps/blobbox.Plo
mv: rename .deps/blobbox.Tpo to .deps/blobbox.Plo: No such file or
directory
make[3]: *** [blobbox.lo] Error 1
make[2]: *** [all-recursive] Error 1
make[1]: *** [all-recursive] Error 1
make: *** [all] Error 2
```

--------------------------------

### Build and install Tesseract with make

Source: https://tesseract-ocr.github.io/tessdoc/ReleaseNotes.html

Standard build and install commands to move data files to the standard location. Required for non-DevStudio users.

```bash
./configure
make
make install

```

--------------------------------

### Install Tesseract to a custom directory

Source: https://tesseract-ocr.github.io/tessdoc/Compiling

Steps to configure and install Tesseract into a local directory without root access.

```bash
./autogen.sh
./configure --prefix=$HOME/local/
make
make install
```

--------------------------------

### Install Tesseract on Fedora 31

Source: https://tesseract-ocr.github.io/tessdoc/InstallationOpenSuse.html

Adds the openSUSE repository and installs Tesseract with the German language pack. Run as root.

```bash
dnf config-manager --add-repo https://download.opensuse.org/repositories/home:Alexander_Pozdnyakov/Fedora_31/home:Alexander_Pozdnyakov.repo
dnf install tesseract
dnf install tesseract-langpack-deu

```

--------------------------------

### Install Tesseract on Fedora 32

Source: https://tesseract-ocr.github.io/tessdoc/InstallationOpenSuse.html

Adds the openSUSE repository and installs Tesseract with the German language pack. Run as root.

```bash
dnf config-manager --add-repo https://download.opensuse.org/repositories/home:Alexander_Pozdnyakov/Fedora_32/home:Alexander_Pozdnyakov.repo
dnf install tesseract
dnf install tesseract-langpack-deu

```

--------------------------------

### Manually build and install OpenMP

Source: https://tesseract-ocr.github.io/tessdoc/Compiling

Alternative method to get, compile, and install OpenMP manually using cmake and git. This method should no longer be needed if libomp is available.

```bash
# Install cmake if it is not available.
sudo port install cmake
git clone https://github.com/llvm-mirror/openmp.git
cd openmp
mkdir build
cd build
cmake ..
make
sudo make install

```

--------------------------------

### GetComponentImages Example

Source: https://tesseract-ocr.github.io/tessdoc/Examples_C%2B%2B.html

Gets textline components from the image, iterates over each box, and prints OCR text and confidence for each.

```C++
#include <tesseract/baseapi.h>
#include <leptonica/allheaders.h>

int main()
{
  char *outText;
  tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
  // Initialize tesseract-ocr with English, without specifying tessdata path
  if (api->Init(NULL, "eng")) {
      fprintf(stderr, "Could not initialize tesseract.\n");
      exit(1);
  }
  Pix *image = pixRead("phototest.tif");
  api->SetImage(image);
  Boxa* boxes = api->GetComponentImages(tesseract::RIL_TEXTLINE, true, NULL, NULL);
  printf("Found %d textline image components.\n", boxes->n);
  for (int i = 0; i < boxes->n; i++) {
    BOX* box = boxaGetBox(boxes, i, L_CLONE);
    api->SetRectangle(box->x, box->y, box->w, box->h);
    char* ocrResult = api->GetUTF8Text();
    int conf = api->MeanTextConf();
    fprintf(stdout, "Box[%d]: x=%d, y=%d, w=%d, h=%d, confidence: %d, text: %s",
                    i, box->x, box->y, box->w, box->h, conf, ocrResult);
    boxDestroy(&box);
  }
  // Destroy used object and release memory
  api->End();
  delete api;
  delete [] outText;
  pixDestroy(&image);

  return 0;
}

```

--------------------------------

### Configure Ubuntu sources.list

Source: https://tesseract-ocr.github.io/tessdoc/Installation.html

If apt cannot find the package, add the universe repository to your sources.list file.

```bash
sudo vi /etc/apt/sources.list

deb http://archive.ubuntu.com/ubuntu bionic universe
```

--------------------------------

### Get LSTM alternative symbol choices and confidence

Source: https://tesseract-ocr.github.io/tessdoc/APIExample.html

This example initializes Tesseract with the English language, sets the 'lstm_choice_mode' variable to 2 to enable alternative symbol choices, and iterates through the result iterator to print symbol confidence and bounding box data.

```cpp
#include <tesseract/baseapi.h>
#include <leptonica/allheaders.h>
int main()
{
    tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
// Initialize tesseract-ocr with English, without specifying tessdata path
    if (api->Init(NULL, "eng")) {
        fprintf(stderr, "Could not initialize tesseract.\n");
        exit(1);
    }
// Open input image with leptonica library
  Pix *image = pixRead("/home/ubuntu/tesseract/test/testing/trainingital.tif");
  api->SetImage(image);
// Set lstm_choice_mode to alternative symbol choices per character, bbox is at word level.
  api->SetVariable("lstm_choice_mode", "2");
  api->Recognize(0);
  tesseract::PageIteratorLevel level = tesseract::RIL_WORD;
  tesseract::ResultIterator* res_it = api->GetIterator();
// Get confidence level for alternative symbol choices. Code is based on
// https://github.com/tesseract-ocr/tesseract/blob/a7a729f6c315e751764b72ea945da961638effc5/src/api/hocrrenderer.cpp#L325-L344
  std::vector<std::vector<std::pair<const char*, float>>>* choiceMap = nullptr;
  if (res_it != 0) {
    do {
      const char* word;
      float conf;
      int x1, y1, x2, y2, tcnt = 1, gcnt = 1, wcnt = 0;
     res_it->BoundingBox(level, &x1, &y1, &x2, &y2);
     choiceMap = res_it->GetBestLSTMSymbolChoices();
      for (auto timestep : *choiceMap) {
        if (timestep.size() > 0) {
          for (auto & j : timestep) {
            conf = int(j.second * 100);
            word =  j.first;
            printf("%d  symbol: '%s';  \tconf: %.2f; BoundingBox: %d,%d,%d,%d;\n",
                        wcnt, word, conf, x1, y1, x2, y2);
           gcnt++;
          }
          tcnt++;
        }
      wcnt++;
      printf("\n");
      }
    } while (res_it->Next(level));
  }
  // Destroy used object and release memory
  api->End();
  delete api;
  pixDestroy(&image);
  return 0;
}
```

--------------------------------

### Find fonts with text2image --find_fonts

Source: https://tesseract-ocr.github.io/tessdoc/Fonts.html

Use this command to find fonts installed on your system that render a given training text. Change the language code and directory locations to match your setup; fontslist.txt will provide text usable in training/language-specific.sh. It will not work for Fraktur fonts and will identify all Latin fonts, so review the generated images and choose appropriate fonts.

```bash
text2image --find_fonts \
--fonts_dir /usr/share/fonts \
--text ./langdata/eng/eng.training_text \
--min_coverage .9  \
--outputbase ./langdata/eng/eng \
|& grep raw \
 | sed -e 's/ :.*/@ \\/g' \
 | sed -e "s/^/  '/" \
 | sed -e "s/@/'/g" >./langdata/eng/fontslist.txt

```

--------------------------------

### Set PKG_CONFIG_PATH for custom Leptonica installation

Source: https://tesseract-ocr.github.io/tessdoc/Compiling

Command to set PKG_CONFIG_PATH to /usr/local/lib/pkgconfig when pkg-config is not looking at the custom install folder. Use this after installing Leptonica in /usr/local.

```bash
PKG_CONFIG_PATH=/usr/local/lib/pkgconfig
```

--------------------------------

### Specify custom install path for Tesseract

Source: https://tesseract-ocr.github.io/tessdoc/Compiling

CMake configuration command to set a custom install prefix, avoiding the need for admin rights to install to Program Files.

```bash
cmake .. -G "Visual Studio 15 2017 Win64" -DCMAKE_INSTALL_PREFIX=inst

```

--------------------------------

### Install fonts on Debian with apt-get

Source: https://tesseract-ocr.github.io/tessdoc/Fonts.html

Install required fonts on Debian GNU Linux and similar distributions (Linux Mint, Ubuntu, etc.) using apt-get. Many font groups are marked as todo and are not yet installed; only DEVANAGARI_FONTS, JPN_FONTS, LATIN_FONTS, and NEOLATIN_FONTS have actual install commands.

```bash
# AMHARIC_FONTS (todo)
# ANCIENT_GREEK_FONTS (todo)
# ARABIC_FONTS (todo)
# ARMENIAN_FONTS (todo)
# BENGALI_FONTS (todo)
# BURMESE_FONTS (todo)
# CHI_SIM_FONTS (todo)
# CHI_TRA_FONTS (todo)

# DEVANAGARI_FONTS (see also external links below)
apt-get install fonts-deva

# EARLY_LATIN_FONTS (todo)
# FRAKTUR_FONTS (todo)
# GEORGIAN_FONTS (todo)
# GREEK_FONTS (todo)
# GUJARATI_FONTS (todo)
# HEBREW_FONTS (todo)

# JPN_FONTS (todo)
apt-get install fonts-noto-cjk fonts-japanese-mincho.ttf fonts-takao-gothic fonts-vlgothic

# KANNADA_FONTS (todo)
# KHMER_FONTS (todo)
# KOREAN_FONTS (todo)
# KURDISH_FONTS (todo)
# KYRGYZ_FONTS (todo)
# LAOTHIAN_FONTS (todo)

# LATIN_FONTS
apt-get install fonts-dejavu gsfonts ttf-mscorefonts-installer

# MALAYALAM_FONTS (todo)

# NEOLATIN_FONTS (still incomplete)
apt-get install fonts-ebgaramond fonts-gfs-didot fonts-gfs-didot-classic fonts-junicode

# NORTH_AMERICAN_ABORIGINAL_FONTS (todo)
# OLD_GEORGIAN_FONTS (todo)
# ORIYA_FONTS (todo)
# PERSIAN_FONTS (todo)
# PUNJABI_FONTS (todo)
# RUSSIAN_FONTS (todo)
# SINHALA_FONTS (todo)
# SYRIAC_FONTS (todo)
# TAMIL_FONTS (todo)
# TELUGU_FONTS (todo)
# THAANA_FONTS (todo)
# THAI_FONTS (todo)
# TIBETAN_FONTS (todo)
# VERTICAL_FONTS (todo)
# VIETNAMESE_FONTS (todo)

```

--------------------------------

### Install Tesseract with Homebrew

Source: https://tesseract-ocr.github.io/tessdoc/Installation.html

Install Tesseract on macOS using the Homebrew package manager.

```bash
brew install tesseract
```

--------------------------------

### Configure with custom options

Source: https://tesseract-ocr.github.io/tessdoc/Compiling-%E2%80%93-GitInstallation.html

Example of running configure with specific flags to disable features and set compiler flags.

```bash
./configure  --disable-openmp --disable-debug --disable-opencl --disable-graphics --disable-shared 'CXXFLAGS=-g -O2 -Wall -Wextra -Wpedantic'
```

--------------------------------

### Configure output showing optional dependencies

Source: https://tesseract-ocr.github.io/tessdoc/tess5/TrainingTesseract-5.html

Expected output from ./configure when all optional dependencies for training tools are available. Look for "yes" for each dependency; version numbers may change over time.

```text
checking for pkg-config... [some valid path]
checking for lept >= 1.74... yes
checking for libarchive... yes
checking for icu-uc >= 52.1... yes
checking for icu-i18n >= 52.1... yes
checking for pango >= 1.22.0... yes
checking for cairo... yes
[...]
```

--------------------------------

### Build training tools with Software Network

Source: https://tesseract-ocr.github.io/tessdoc/Compiling

Command to build training tools using the Software Network client, which creates a solution link in the root directory.

```bash
sw build

```

--------------------------------

### C++ API Example for user patterns

Source: https://tesseract-ocr.github.io/tessdoc/APIExample-user_patterns.html

A C++ program demonstrating how to initialize Tesseract with a config file containing user patterns.

```cpp
#include <tesseract/baseapi.h>
#include <leptonica/allheaders.h>

int main()
{
    Pix *image;
    char *outText;
    char *configs[]={"path/to/my.patterns.config"};
    int configs_size = 1;
    tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
    if (api->Init(NULL, "eng", tesseract::OEM_LSTM_ONLY, configs, configs_size, NULL, NULL, false)) {
      fprintf(stderr, "Could not initialize tesseract.\n");
      exit(1);
    }
    image = pixRead("Arial.png");
    api->SetImage(image);
    outText = api->GetUTF8Text();
    printf(outText);
    api->End();
    delete api;
    delete [] outText;
    pixDestroy(&image);
    return 0;
}
```

--------------------------------

### Install required libraries for training tools

Source: https://tesseract-ocr.github.io/tessdoc/tess5/TrainingTesseract-5.html

Command to install the necessary dependencies for building Tesseract training tools on Debian-based Linux systems.

```bash
sudo apt-get install libicu-dev libpango1.0-dev libcairo2-dev
```

--------------------------------

### Install Leptonica development package

Source: https://tesseract-ocr.github.io/tessdoc/Compiling

Command to install the Leptonica development headers from the distribution package manager.

```bash
sudo apt-get install libleptonica-dev
```

--------------------------------

### Install Tesseract with MacPorts

Source: https://tesseract-ocr.github.io/tessdoc/Installation.html

Commands to install the Tesseract base package and additional language data via MacPorts.

```bash
sudo port install tesseract
```

```bash
sudo port install tesseract-<langcode>
```

--------------------------------

### Example of a config file

Source: https://tesseract-ocr.github.io/tessdoc/APIExample-user_patterns.html

A configuration file that specifies the path to the user patterns file using the user_patterns_file key.

```text
user_patterns_file path/to/my.patterns



```

--------------------------------

### Install Tesseract on openSUSE Leap 15.0

Source: https://tesseract-ocr.github.io/tessdoc/InstallationOpenSuse.html

Adds the openSUSE repository, refreshes the package list, and installs Tesseract OCR with the German traineddata. Run as root.

```bash
zypper addrepo https://download.opensuse.org/repositories/home:Alexander_Pozdnyakov/openSUSE_Leap_15.0/home:Alexander_Pozdnyakov.repo
zypper refresh
zypper install tesseract-ocr
zypper install tesseract-ocr-traineddata-german

```
Tokens:
Raw