C++ Examples

Basic_example

#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);
    }

    // Open input image with leptonica library
    Pix *image = pixRead("phototest.tif");
    api->SetImage(image);
    // Get OCR result
    outText = api->GetUTF8Text();
    printf("OCR output:\n%s", outText);

    // Destroy used object and release memory
    api->End();
    delete api;
    delete [] outText;
    pixDestroy(&image);

    return 0;
}

SetRectangle_example

#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);
    }

    // Open input image with leptonica library
    Pix *image = pixRead("phototest.tif");
    api->SetImage(image);
    // Restrict recognition to a sub-rectangle of the image
    // SetRectangle(left, top, width, height)
    api->SetRectangle(30, 86, 590, 100);
    // Get OCR result
    outText = api->GetUTF8Text();
    printf("OCR output:\n%s", outText);

    // Destroy used object and release memory
    api->End();
    delete api;
    delete [] outText;
    pixDestroy(&image);

    return 0;
}

GetComponentImages_example

#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;
}

ResultIterator_example

#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);
  api->Recognize(0);
  tesseract::ResultIterator* ri = api->GetIterator();
  tesseract::PageIteratorLevel level = tesseract::RIL_WORD;
  if (ri != 0) {
    do {
      const char* word = ri->GetUTF8Text(level);
      float conf = ri->Confidence(level);
      int x1, y1, x2, y2;
      ri->BoundingBox(level, &x1, &y1, &x2, &y2);
      printf("word: '%s';  \tconf: %.2f; BoundingBox: %d,%d,%d,%d;\n",
               word, conf, x1, y1, x2, y2);
      delete[] word;
    } while (ri->Next(level));
  }
  // Destroy used object and release memory
  api->End();
  delete api;
  delete [] outText;
  pixDestroy(&image);
  return 0;
}

OSD_example

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

int main()
{
    const char* inputfile = "devatest-rotated-270.png";
    PIX *image = pixRead(inputfile);
    tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
    api->Init(NULL, "osd");
    api->SetPageSegMode(tesseract::PSM_OSD_ONLY);
    api->SetImage(image);
        
    int orient_deg;
    float orient_conf;
    const char* script_name;
    float script_conf;
    api->DetectOrientationScript(&orient_deg, &orient_conf, &script_name, &script_conf);
    printf("************\n Orientation in degrees: %d\n Orientation confidence: %.2f\n"
    " Script: %s\n Script confidence: %.2f\n",
    orient_deg, orient_conf,
    script_name, script_conf);
    
    // Destroy used object and release memory
    api->End();
    delete api;
    pixDestroy(&image);
    
    return 0;
}

LSTM_Choices_example

#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("choices.png");
  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/main/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;
}

OpenCV_example

/*
  Windows compile example:
  
  SET TESS_INSTALLATION=C:/win64
  SET OPENCV_INSTALLATION=C:/opencv/build
  cl OpenCV_example.cc -I %TESS_INSTALLATION%/include -I %OPENCV_INSTALLATION%/include /link /LIBPATH:%TESS_INSTALLATION%/lib /LIBPATH:%OPENCV_INSTALLATION%/x64/vc14/lib tesseract51.lib leptonica-1.83.0.lib opencv_world460.lib /machine:x64
  
*/

#include <leptonica/allheaders.h>
#include <opencv2/opencv.hpp>
#include <string>
#include <tesseract/baseapi.h>

int main(int argc, char *argv[]) {

  std::string outText, imPath = argv[1];
  cv::Mat im = cv::imread(imPath, cv::IMREAD_COLOR);
  tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();

  api->Init(NULL, "eng", tesseract::OEM_LSTM_ONLY);
  api->SetPageSegMode(tesseract::PSM_AUTO);
  api->SetImage(im.data, im.cols, im.rows, 3, im.step);
  outText = std::string(api->GetUTF8Text());
  std::cout << outText;
  api->End();
  delete api;
  return 0;
}

UserPatterns_example

#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;
}