【OpenCV】How to Use Tesseract with C++ or OpenCV

说明：在使用Tesseract 之前，一定要安装好Tesseract ，并在Project中配置好Tesseract 路径。

在自己的工程属性中VC++目录下增加包含目录和库目录，以便VS2010查找文件。例如：

包含目录：新增C:\Program Files\Tesseract-OCR\include\tesseract

库目录：新增C:\Program Files\Tesseract-OCR\include\lib

1. Tesseract 在C++中直接使用

// tess.cpp: 
// Recognize text on an image using Tesseract API and print it to the screen
// Usage: ./tess image.png

#include <tesseract/baseapi.h>
#include <tesseract/strngs.h>
#include <iostream>

int main(int argc, char** argv)
{
    if (argc != 2)
    {
        std::cout << "Please specify the input image!" << std::endl;
        return -1;
    }

    const char* lang = "eng";  //简体中文chi_sim
    const char* filename = argv[1];

    //新建tess基类
    tesseract::TessBaseAPI tess;

    //初始化
    tess.Init(NULL, lang, tesseract::OEM_DEFAULT);


    //设置识别模式
    tess.SetPageSegMode(tesseract::PSM_SINGLE_BLOCK);

    FILE* fin = fopen(filename, "rb");
    if (fin == NULL)
    {
        std::cout << "Cannot open " << filename << std::endl;
        return -1;
    }
    fclose(fin);

    STRING text;

    //进行识别
    if (!tess.ProcessPages(filename, NULL, 0, &text))
    {
        std::cout << "Error during processing." << std::endl;
        return -1;
    }
    else
        std::cout << text.string() << std::endl;

    return 0;
}

进行OCR识别的主题函数为tesseract::TessBaseAPI:: bool TessBaseAPI::ProcessPage(Pix* pix, int page_index, const char* filename,                                                                                                           const char* retry_config, int timeout_millisec,STRING* textout);            在分析流程时，专注此API，位置在baseapi.cpp

2. Tesseract同OpenCV结合使用

可以选择ROI然后进行OCR，为了识别cv::Mat矩阵，将其传递至TessBaseAPI::SetImage(); 使用TessBaseAPI::GetUTF8Text()得到识别后的文字。

// tesscv.cpp:
// Using Tesseract API with OpenCV

#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <tesseract/baseapi.h>
#include <iostream>

int main(int argc, char** argv)
{
    // Usage: tesscv image.png
    if (argc != 2)
    {
        std::cout << "Please specify the input image!" << std::endl;
        return -1;
    }

    // Load image
    cv::Mat im = cv::imread(argv[1]);
    if (im.empty())
    {
        std::cout << "Cannot open source image!" << std::endl;
        return -1;
    }

    cv::Mat gray;
    cv::cvtColor(im, gray, CV_BGR2GRAY);
    // ...other image pre-processing here...

    // Pass it to Tesseract API
    tesseract::TessBaseAPI tess;
    tess.Init(NULL, "eng", tesseract::OEM_DEFAULT);
    tess.SetPageSegMode(tesseract::PSM_SINGLE_BLOCK);
    tess.SetImage((uchar*)gray.data, gray.cols, gray.rows, 1, gray.cols);

    // Get the text
    char* out = tess.GetUTF8Text();
    std::cout << out << std::endl;

    return 0;
}