如何使用 C++ 和 Dynamsoft 的精细调整深度学习模型构建桌面 MRZ 扫描仪

机器可读区 (MRZ)使用的字体称为OCR-B，该字体已标准化并在全球范围内统一。在最新版本的 Capture Vision SDK 中，Dynamsoft 发布了用于 MRZ 识别的全新深度学习模型。该模型已在大量 MRZ 样本数据集上进行训练，并在 MRZ 文本识别方面提供了显著更高的准确率。在本文中，我们将演示如何使用 C++ 和 Dynamsoft 经过精细调整的深度学习模型构建桌面 MRZ 扫描仪。

C++ MRZ 扫描仪演示视频

先决条件

MRZ深度学习模型

解压 SDK 压缩包后，您可以在文件夹中找到模型文件DynamsoftCaptureVision\Dist\Models。模型文件大小小于 2MB。

MRZ深度学习模型

与上一版本相比，新模型将Dynamsoft MRZ数据集的识别准确率从65%提升至95%，性能实现了显著飞跃。

MRZ识别深度学习模型

如何配置 CMakeLists.txt 文件

MRZ 扫描仪应用程序需要访问摄像头。我们使用Litecam来捕捉视频帧。

在文件中CMakeLists.txt：

  1. 编译源代码文件并链接 litecam 和 Dynamsoft Capture Vision 库。用于确定WindowsCMAKE_BUILD_TYPE的运行时库和链接目录。

    cmake_minimum_required(VERSION 3.15)
 project(MRZScanner)
    
 if(WIN32)
     if (CMAKE_BUILD_TYPE STREQUAL "Debug")
         set(CMAKE_MSVC_RUNTIME_LIBRARY "MultiThreadedDebug")
     else()
         set(CMAKE_MSVC_RUNTIME_LIBRARY "MultiThreaded") 
     endif()
        
     if(CMAKE_BUILD_TYPE STREQUAL "Release")
         link_directories(${CMAKE_CURRENT_SOURCE_DIR}/../../dist/lib/windows/release ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/platforms/win/lib)
     else()
         link_directories(${CMAKE_CURRENT_SOURCE_DIR}/../../dist/lib/windows/debug ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/platforms/win/lib)
     endif()
        
     set(DBR_LIBS "DynamsoftCorex64" "DynamsoftLicensex64" "DynamsoftCaptureVisionRouterx64" "DynamsoftUtilityx64")
    
 elseif(APPLE)
     set(CMAKE_CXX_FLAGS "-std=c++11 -O3 -Wl,-rpath,@executable_path")
     set(CMAKE_INSTALL_RPATH "@executable_path")
    
     link_directories(
         ${CMAKE_CURRENT_SOURCE_DIR}/../../dist/lib/macos
         ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/platforms/macos
     )
    
     set(DBR_LIBS
         "DynamsoftCore"
         "DynamsoftLicense"
         "DynamsoftCaptureVisionRouter"
         "DynamsoftUtility"
         "pthread"
     )
 elseif(UNIX)
     SET(CMAKE_CXX_FLAGS "-std=c++11 -O3 -Wl,-rpath=$ORIGIN")
     SET(CMAKE_INSTALL_RPATH "$ORIGIN")
     link_directories(${CMAKE_CURRENT_SOURCE_DIR}/../../dist/lib/linux ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/platforms/linux)
     set(DBR_LIBS "DynamsoftCore" "DynamsoftLicense" "DynamsoftCaptureVisionRouter" "DynamsoftUtility" pthread)
 endif()
    
 add_executable(${PROJECT_NAME} main.cpp)
 target_include_directories(${PROJECT_NAME} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/../../dist/include ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/include)
 target_link_libraries(${PROJECT_NAME} litecam ${DBR_LIBS})

  2. 将资源（包括模板、模型和共享库）复制到输出目录。确保资源名称和结构与 Dynamsoft Capture Vision SDK 保持一致。

    if(WIN32)
     if(CMAKE_BUILD_TYPE STREQUAL "Release")
         add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
         COMMAND ${CMAKE_COMMAND} -E copy_directory
         ${CMAKE_CURRENT_SOURCE_DIR}/../../dist/lib/windows/release   
         $<TARGET_FILE_DIR:${PROJECT_NAME}>)
     else()
         add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
         COMMAND ${CMAKE_COMMAND} -E copy_directory
         ${CMAKE_CURRENT_SOURCE_DIR}/../../dist/lib/windows/debug   
         $<TARGET_FILE_DIR:${PROJECT_NAME}>)
     endif()
    
     add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
     COMMAND ${CMAKE_COMMAND} -E copy_directory
     ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/platforms/win/bin/      
     $<TARGET_FILE_DIR:${PROJECT_NAME}>)
 elseif(APPLE)
     add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
         COMMAND ${CMAKE_COMMAND} -E copy_directory
         ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/platforms/macos
         $<TARGET_FILE_DIR:${PROJECT_NAME}>
     )
 elseif(UNIX)
     add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
     COMMAND ${CMAKE_COMMAND} -E copy_directory
     ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/platforms/linux/      
     $<TARGET_FILE_DIR:${PROJECT_NAME}>)
 endif()
    
    
 add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
 COMMAND ${CMAKE_COMMAND} -E make_directory $<TARGET_FILE_DIR:${PROJECT_NAME}>/Templates
 COMMAND ${CMAKE_COMMAND} -E copy_directory
 ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/Templates
 $<TARGET_FILE_DIR:${PROJECT_NAME}>/Templates)
    
 add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
 COMMAND ${CMAKE_COMMAND} -E make_directory $<TARGET_FILE_DIR:${PROJECT_NAME}>/Models
 COMMAND ${CMAKE_COMMAND} -E copy_directory
 ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/Models
 $<TARGET_FILE_DIR:${PROJECT_NAME}>/Models)
    
 add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
 COMMAND ${CMAKE_COMMAND} -E make_directory $<TARGET_FILE_DIR:${PROJECT_NAME}>/ParserResources
 COMMAND ${CMAKE_COMMAND} -E copy_directory
 ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/ParserResources
 $<TARGET_FILE_DIR:${PROJECT_NAME}>/ParserResources)
    
 add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
 COMMAND ${CMAKE_COMMAND} -E copy
 ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/ConfusableChars.data
 $<TARGET_FILE_DIR:${PROJECT_NAME}>/ConfusableChars.data)
    
 add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
 COMMAND ${CMAKE_COMMAND} -E copy
 ${CMAKE_CURRENT_SOURCE_DIR}/../../../examples/10.x/sdk/OverlappingChars.data
 $<TARGET_FILE_DIR:${PROJECT_NAME}>/OverlappingChars.data)

    Dynamsoft Capture Vision 资源

使用 C++ 实现 MRZ 扫描仪的步骤

在接下来的步骤中，我们将逐步完成main.cpp实现 MRZ 扫描仪的文件。

步骤 1：包含头文件

#include <iostream>
#include <deque>
#include <vector>
#include <mutex>
#include <string>
#include "DynamsoftCaptureVisionRouter.h"
#include "DynamsoftUtility.h"
#include "Camera.h"
#include "CameraPreview.h"

using namespace std;
using namespace dynamsoft::license;
using namespace dynamsoft::dlr;
using namespace dynamsoft::cvr;
using namespace dynamsoft::utility;
using namespace dynamsoft::basic_structures;
using namespace dynamsoft::dcp;

步骤2：初始化图像处理引擎

  1. 使用您自己的许可证密钥设置。

     int iRet = -1;
 char szErrorMsg[256];
 iRet = CLicenseManager::InitLicense("LICENSE-KEY", szErrorMsg, 256);
 if (iRet != EC_OK)
 {
     std::cout << szErrorMsg << std::endl;
 }

  2. 实例化CCaptureVisionRouter、MyVideoFetcher和CCapturedResultReceiver。CCaptureVisionRouter管理图像处理的工作流程。MyVideoFetcher是 的子类CImageSourceAdapter，用于获取视频帧。CCapturedResultReceiver是 的子类CCapturedResultReceiver，用于接收 MRZ 识别结果。

    class MyCapturedResultReceiver : public CCapturedResultReceiver
 {
 public:
     virtual void OnCapturedResultReceived(CCapturedResult *capturedResult) override
     {
         // TODO: process the MRZ text
     }
 };
    
 class MyVideoFetcher : public CImageSourceAdapter
 {
 public:
     MyVideoFetcher() {}
     ~MyVideoFetcher() {}
    
     bool HasNextImageToFetch() const override
     {
         return true;
     }
    
     void MyAddImageToBuffer(const CImageData *img, bool bClone = true)
     {
         AddImageToBuffer(img, bClone);
     }
 };

 int main()
 {
     int errorCode = 0;
     char errorMsg[512] = {0};
     CCaptureVisionRouter *cvr = new CCaptureVisionRouter;
    
     MyVideoFetcher *fetcher = new MyVideoFetcher();
     fetcher->SetMaxImageCount(4);
     fetcher->SetBufferOverflowProtectionMode(BOPM_UPDATE);
     fetcher->SetColourChannelUsageType(CCUT_AUTO);
     cvr->SetInput(fetcher);
    
     CCapturedResultReceiver *capturedReceiver = new MyCapturedResultReceiver;
     cvr->AddResultReceiver(capturedReceiver);
    
     errorCode = cvr->StartCapturing("ReadPassportAndId", false, errorMsg, 512);
     if (errorCode != EC_OK)
     {
         std::cout << "error:" << errorMsg << std::endl;
         return -1;
     }
 }

步骤 3：创建相机对象并启动相机预览

  1. 创建一个Camera对象并循环捕获视频帧。

    Camera camera;

 if (camera.Open(0))
 {
     CameraWindow window(camera.frameWidth, camera.frameHeight, "Camera Stream");
     if (!window.Create())
     {
         std::cerr << "Failed to create window." << std::endl;
         return -1;
     }
     window.Show();

     CameraWindow::Color textColor = {255, 0, 0};
     while (window.WaitKey('q'))
     {
         FrameData frame = camera.CaptureFrame();
         if (frame.rgbData)
         {
             window.ShowFrame(frame.rgbData, frame.width, frame.height);
             // Process the frame
             ReleaseFrame(frame);
         }
     }

     camera.Release();
 }

  2. 将帧附加到MyVideoFetcher对象以进行 MRZ 识别。

     if (frame.rgbData)
 {
     window.ShowFrame(frame.rgbData, frame.width, frame.height);

     CImageData data(frame.size,
                     frame.rgbData,
                     frame.width,
                     frame.height,
                     frame.width * 3,
                     IPF_RGB_888,
                     0, 0);

     fetcher->MyAddImageToBuffer(&data);
 }

步骤4：在回调函数中接收MRZ识别结果

  1. OnCapturedResultReceivedMRZ 识别过程完成后触发回调函数。MRZ 文本存储在对象中CCapturedResult。

     class Point
 {
    
 public:
     int x;
     int y;
     Point(int x, int y) : x(x), y(y) {}
 };
    
 struct TextResult
 {
     int id;
     MRZResult info;
     std::vector<Point> textLinePoints;
 };
    
 std::vector<TextResult> textResults;
 std::mutex textResultsMutex;
    
 class MyCapturedResultReceiver : public CCapturedResultReceiver
 {
 public:
     virtual void OnCapturedResultReceived(CCapturedResult *capturedResult) override
     {
         std::lock_guard<std::mutex> lock(textResultsMutex);
         textResults.clear();
    
         CRecognizedTextLinesResult *textLineResult = capturedResult->GetRecognizedTextLinesResult();
         if (textLineResult == nullptr)
         {
             return;
         }
    
         int lCount = textLineResult->GetItemsCount();
         for (int li = 0; li < lCount; ++li)
         {
             TextResult textResult;
    
             const CTextLineResultItem *textLine = textLineResult->GetItem(li);
             CPoint *points = textLine->GetLocation().points;
             textResult.textLinePoints.push_back(Point(points[0][0], points[0][1]));
             textResult.textLinePoints.push_back(Point(points[1][0], points[1][1]));
             textResult.textLinePoints.push_back(Point(points[2][0], points[2][1]));
             textResult.textLinePoints.push_back(Point(points[3][0], points[3][1]));
    
             const CParsedResultItem *item = capturedResult->GetParsedResult()->GetItem(li);
             MRZResult mrzResult;
             mrzResult.FromParsedResultItem(item);
    
             textResult.info = mrzResult;
    
             textResults.push_back(textResult);
         }
     }
 };

  2. 该FromParsedResultItem()功能从MRZ文本中提取证件类型、签发国、证件号码、姓名、国籍、出生日期、性别、有效期等标准化信息。

    class MRZResult
 {
 public:
     string docId;
     string docType;
     string nationality;
     string issuer;
     string dateOfBirth;
     string dateOfExpiry;
     string gender;
     string surname;
     string givenname;
    
     vector<string> rawText;
    
     MRZResult FromParsedResultItem(const CParsedResultItem *item)
     {
         docType = item->GetCodeType();
    
         if (docType == "MRTD_TD3_PASSPORT")
         {
             if (item->GetFieldValidationStatus("passportNumber") != VS_FAILED && item->GetFieldValue("passportNumber") != NULL)
             {
                 docId = item->GetFieldValue("passportNumber");
             }
         }
         else if (item->GetFieldValidationStatus("documentNumber") != VS_FAILED && item->GetFieldValue("documentNumber") != NULL)
         {
             docId = item->GetFieldValue("documentNumber");
         }
    
         string line;
         if (docType == "MRTD_TD1_ID")
         {
             if (item->GetFieldValue("line1") != NULL)
             {
                 line = item->GetFieldValue("line1");
                 if (item->GetFieldValidationStatus("line1") == VS_FAILED)
                 {
                     line += ", Validation Failed";
                 }
                 rawText.push_back(line);
             }
    
             if (item->GetFieldValue("line2") != NULL)
             {
                 line = item->GetFieldValue("line2");
                 if (item->GetFieldValidationStatus("line2") == VS_FAILED)
                 {
                     line += ", Validation Failed";
                 }
                 rawText.push_back(line);
             }
    
             if (item->GetFieldValue("line3") != NULL)
             {
                 line = item->GetFieldValue("line3");
                 if (item->GetFieldValidationStatus("line3") == VS_FAILED)
                 {
                     line += ", Validation Failed";
                 }
                 rawText.push_back(line);
             }
         }
         else
         {
             if (item->GetFieldValue("line1") != NULL)
             {
                 line = item->GetFieldValue("line1");
                 if (item->GetFieldValidationStatus("line1") == VS_FAILED)
                 {
                     line += ", Validation Failed";
                 }
                 rawText.push_back(line);
             }
    
             if (item->GetFieldValue("line2") != NULL)
             {
                 line = item->GetFieldValue("line2");
                 if (item->GetFieldValidationStatus("line2") == VS_FAILED)
                 {
                     line += ", Validation Failed";
                 }
                 rawText.push_back(line);
             }
         }
    
         if (item->GetFieldValidationStatus("nationality") != VS_FAILED && item->GetFieldValue("nationality") != NULL)
         {
             nationality = item->GetFieldValue("nationality");
         }
         if (item->GetFieldValidationStatus("issuingState") != VS_FAILED && item->GetFieldValue("issuingState") != NULL)
         {
             issuer = item->GetFieldValue("issuingState");
         }
         if (item->GetFieldValidationStatus("dateOfBirth") != VS_FAILED && item->GetFieldValue("dateOfBirth") != NULL)
         {
             dateOfBirth = item->GetFieldValue("dateOfBirth");
         }
         if (item->GetFieldValidationStatus("dateOfExpiry") != VS_FAILED && item->GetFieldValue("dateOfExpiry") != NULL)
         {
             dateOfExpiry = item->GetFieldValue("dateOfExpiry");
         }
         if (item->GetFieldValidationStatus("sex") != VS_FAILED && item->GetFieldValue("sex") != NULL)
         {
             gender = item->GetFieldValue("sex");
         }
         if (item->GetFieldValidationStatus("primaryIdentifier") != VS_FAILED && item->GetFieldValue("primaryIdentifier") != NULL)
         {
             surname = item->GetFieldValue("primaryIdentifier");
         }
         if (item->GetFieldValidationStatus("secondaryIdentifier") != VS_FAILED && item->GetFieldValue("secondaryIdentifier") != NULL)
         {
             givenname = item->GetFieldValue("secondaryIdentifier");
         }
    
         return *this;
     }
    
     string ToString()
     {
         string msg = "Raw Text:\n";
         for (size_t idx = 0; idx < rawText.size(); ++idx)
         {
             msg += "\tLine " + to_string(idx + 1) + ": " + rawText[idx] + "\n";
         }
         msg += "Parsed Information:\n";
         msg += "\tDocument Type: " + docType + "\n";
         msg += "\tDocument ID: " + docId + "\n";
         msg += "\tSurname: " + surname + "\n";
         msg += "\tGiven Name: " + givenname + "\n";
         msg += "\tNationality: " + nationality + "\n";
         msg += "\tIssuing Country or Organization: " + issuer + "\n";
         msg += "\tGender: " + gender + "\n";
         msg += "\tDate of Birth(YYMMDD): " + dateOfBirth + "\n";
         msg += "\tExpiration Date(YYMMDD): " + dateOfExpiry + "\n";
    
         return msg;
     }
 };

步骤5：在屏幕上显示MRZ文本


{
    std::lock_guard<std::mutex> lock(textResultsMutex);
    for (const auto &result : textResults)
    {
        if (!result.textLinePoints.empty())
        {
            std::vector<std::pair<int, int>> corners = {{result.textLinePoints[0].x, result.textLinePoints[0].y},
                                                        {result.textLinePoints[1].x, result.textLinePoints[1].y},
                                                        {result.textLinePoints[2].x, result.textLinePoints[2].y},
                                                        {result.textLinePoints[3].x, result.textLinePoints[3].y}};
            window.DrawContour(corners);

            int x = 20;
            int y = 40;

            MRZResult mrzResult = result.info;
            string msg = "Document Type: " + mrzResult.docType;
            window.DrawText(msg, x, y, 24, textColor);
            y += 20;
            msg = "Document ID: " + mrzResult.docId;
            window.DrawText(msg, x, y, 24, textColor);
            y += 20;
            msg = "Surname: " + mrzResult.surname;
            window.DrawText(msg, x, y, 24, textColor);
            y += 20;
            msg = "Given Name: " + mrzResult.givenname;
            window.DrawText(msg, x, y, 24, textColor);
            y += 20;
            msg = "Nationality: " + mrzResult.nationality;
            window.DrawText(msg, x, y, 24, textColor);
            y += 20;
            msg = "Issuing Country or Organization: " + mrzResult.issuer;
            window.DrawText(msg, x, y, 24, textColor);
            y += 20;
            msg = "Gender: " + mrzResult.gender;
            window.DrawText(msg, x, y, 24, textColor);
            y += 20;
            msg = "Date of Birth(YYMMDD): " + mrzResult.dateOfBirth;
            window.DrawText(msg, x, y, 24, textColor);
            y += 20;
            msg = "Expiration Date(YYMMDD): " + mrzResult.dateOfExpiry;
        }
    }
}

步骤 6：构建并运行 MRZ 扫描仪

  1. 创建构建目录：

    mkdir build
 cd build

  2. 使用 CMake 配置并构建：

    cmake ..
 cmake --build .

    C++ MRZ 扫描仪

源代码

https://github.com/yushulx/cmake-cpp-barcode-qrcode-mrz/tree/main/litecam/examples/mrz

# c++ # 深度学习 # 开发语言
Logo
腾讯云开发者社区

腾讯云面向开发者汇聚海量精品云计算使用和开发经验，营造开放的云计算技术生态圈。

更多推荐

终极指南：Flink SQL连接器版本管理从混乱到有序的升级之路

Apache Flink作为流处理领域的佼佼者，其SQL连接器的版本管理一直是开发者面临的核心挑战。本文将系统讲解Flink SQL连接器版本管理的最佳实践，帮助你轻松应对版本兼容性问题，实现从混乱到有序的升级之旅。## 连接器版本管理的常见痛点 😫在Flink应用开发中，连接器版本管理常常让开发者头疼不已。不同版本的连接器可能导致各种兼容性问题，例如API变更、功能差异甚至运行时错误。

avatar 腾讯云开发者社区

Elasticsearch复杂数据类型终极指南：从入门到精通

Elasticsearch作为功能强大的搜索引擎，支持多种复杂数据类型，让开发者能够灵活处理各种结构化和非结构化数据。本文将带你全面了解Elasticsearch中的复杂数据类型，从基础概念到实际应用，助你轻松掌握数据建模的核心技巧。## 内部对象：构建层级化数据结构在Elasticsearch中，对象类型（Object）是最基础的复杂数据类型之一，用于表示具有嵌套关系的数据。例如，我们可

avatar 腾讯云开发者社区

如何快速搭建Neon无服务器PostgreSQL：面向初学者的完整指南

Neon是一款革命性的无服务器PostgreSQL解决方案，它通过分离存储和计算层，实现了自动扩缩容、类代码式数据库分支以及零级扩展能力。本指南将帮助你从零开始搭建Neon开发环境，体验这款创新数据库的强大功能。## 准备工作：环境要求与依赖项在开始搭建Neon环境前，请确保你的系统满足以下要求：- Linux操作系统（推荐Ubuntu 20.04+或Debian 11+）- Git

avatar 腾讯云开发者社区