Tesseract BasicExample.cpp

// 參照 Tesseract API for VS2017
// 整張圖片一次辨識
#include "pch.h"
#include <iostream>

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

int main()
{
char *outText = NULL;
tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
// 英文加中文
if (api->Init(NULL, "eng+chi_tra")) {
std::cerr << "Could not initialize tesseract.\n";
}
Pix *image = pixRead("D:\\TensorFlow\\OCR\\bbb.png");
// 以下兩行，可 擇一 或 都不執行
api->SetPageSegMode(tesseract::PSM_SINGLE_BLOCK); // 預設值
//api->SetPageSegMode(tesseract::PSM_SINGLE_LINE);
api->SetImage(image);
//api->SetRectangle(40, 5, 150, 30);
outText = api->GetUTF8Text();
// 要顯示中文要經很多轉換
int len = ::MultiByteToWideChar(CP_UTF8, NULL, outText, -1, NULL, 0);
wchar_t* wszString = new wchar_t[len + 1];
::MultiByteToWideChar(CP_UTF8, NULL, outText, -1, wszString, len);
wszString[len] = '\0';
len = ::WideCharToMultiByte(CP_ACP, 0, wszString, -1, NULL, 0, NULL, NULL);
char* szBig5 = new char[len + 1];
::WideCharToMultiByte(CP_ACP, 0, wszString, -1, szBig5, len, NULL, NULL);
szBig5[len] = '\0';

std::cout << "=======================\n";
std::cout << outText << "\n";
std::cout << "=======================\n";
std::cout << wszString << "\n";
std::cout << "=======================\n";
std::cout << szBig5 << "\n";
std::cout << "=======================\n";
api->End();
if (outText) delete[] outText;
if (wszString) delete[] wszString;
pixDestroy(&image);
}