Passport MRZ Recognition with Dynamsoft C++ OCR SDK

Initialize the OCR object. A valid license key is required.

CLabelRecognition dlr;
dlr.InitLicense("LICENSE-KEY");

Append a template file.

int ret = dlr.AppendSettingsFromFile("template-file");

Note: if the DirectoryPath configured in the template file is a relative path, you must put the template file along with the model folder.

"CharacterModelArray" : [
{
  "DirectoryPath": "CharacterModel",
  "FilterFilePath": "",
  "Name": "NumberUppercase"
}
],

Call OCR recognition method. We can use the built-in function of OpenCV to measure the passing time. The TickMeter class simplifies the code of time calculation for Windows and Linux.

TickMeter tm;
tm.start();
errorCode = dlr.RecognizeByFile(pszImageFile, "locr");
tm.stop();
float costTime = tm.getTimeSec();

Get the text recognition results that include the coordinate of the text zone, text lines, and text strings.

DLRResultArray* pDLRResults = NULL;
    dlr.GetAllDLRResults(&pDLRResults);
    if (pDLRResults != NULL)
    {
        int rCount = pDLRResults->resultsCount;
        printf("\r\nRecognized %d results\r\n", rCount);
        for (int ri = 0; ri < rCount; ++ri)
        {
            printf("\r\nResult %d :\r\n", ri);
            int startX = 50, startY = 50;
            DLRResult* result = pDLRResults->results[ri];
            int lCount = result->lineResultsCount;
            for (int li = 0; li < lCount; ++li)
            {
                printf("Line result %d: %s\r\n", li, result->lineResults[li]->text);
                DLRPoint *points = result->lineResults[li]->location.points;
                printf("x1: %d, y1: %d, x2: %d, y2: %d, x3: %d, y3: %d, x4: %d, y4: %d\r\n", points[0].x, 
                points[0].y, points[1].x, points[1].y, points[2].x, points[2].y, points[3].x, points[3].y);
            }
        }
    }
    else
    {
        printf("\r\nNo data detected.\r\n");
    }
    dlr.FreeDLRResults(&pDLRResults);

Parse the MRZ string and extract the corresponding information.

string line1 = result->lineResults[0]->text;
string line2 = result->lineResults[1]->text;
// https://en.wikipedia.org/wiki/Machine-readable_passport
// Type
string tmp = "Type: ";
tmp.insert(tmp.length(), 1, line1[0]);
printf("%s\r\n", tmp.c_str());

// Issuing country
tmp = "Issuing country: "; line1.substr(2, 5);
tmp += line1.substr(2, 3);      
printf("%s\r\n", tmp.c_str());

// Surname
int index = 5;
tmp = "Surname: ";
for (; index < 44; index++)
{
  if (line1[index] != '<')
  {
    tmp.insert(tmp.length(), 1, line1[index]);
  }
  else 
  {
    break;
  }
}
printf("%s\r\n", tmp.c_str());

// Given names
tmp = "Given Names: ";
index += 2;
for (; index < 44; index++)
{
  if (line1[index] != '<')
  {
    tmp.insert(tmp.length(), 1, line1[index]);
  }
  else 
  {
    tmp.insert(tmp.length(), 1, ' ');
  }
}
printf("%s\r\n", tmp.c_str());

// Passport number
tmp = "Passport number: ";
index = 0;
for (; index < 9; index++)
{
  if (line2[index] != '<')
  {
    tmp.insert(tmp.length(), 1, line2[index]);
  }
  else 
  {
    break;
  }
}
printf("%s\r\n", tmp.c_str());

// Nationality
tmp = "Nationality: ";
tmp += line2.substr(10, 3);
printf("%s\r\n", tmp.c_str());

// Date of birth
tmp = line2.substr(13, 6);
tmp.insert(2, "/");
tmp.insert(5, "/");
tmp = "Date of birth (YYMMDD): " + tmp;
printf("%s\r\n", tmp.c_str());

// Sex
tmp = "Sex: ";
tmp.insert(tmp.length(), 1, line2[20]);
printf("%s\r\n", tmp.c_str());

// Expiration date of passport
tmp = line2.substr(21, 6);
tmp.insert(2, "/");
tmp.insert(5, "/");
tmp = "Expiration date of passport (YYMMDD): " + tmp;
printf("%s\r\n", tmp.c_str());

// Personal number
if (line2[28] != '<')
{
  tmp = "Personal number: ";
  for (index = 28; index < 42; index++)
  {
    if (line2[index] != '<')
    {
      tmp.insert(tmp.length(), 1, line2[index]);
    }
    else 
    {
      break;
    }
  }
  printf("%s\r\n", tmp.c_str());
}