VS2015+Tesseract4配置与示例（修改版）全套库类实例

声明本文的资源及内容引用这位仁兄（https://blog.****.net/andylanzhiyong/article/details/81807425）的文章

我只不过是增加了一个50.2MB的最新识别库罢了（识别率更高了些）

增加了最新中文识别库 50.2MB的那个！

整套资源下载地址：https://download.****.net/download/blackangelboy/12255296

附上代码

附上下载修改版VS2015+Tesseract4全套编译库地址

#include<iostream>
#include <stdio.h>
#include<windows.h>
#include "leptonica/allheaders.h"
#include "tesseract/capi.h"
using namespace std;

void die(const char *errstr) {
fputs(errstr, stderr);
exit(1);
}

void ConvertUtf8ToGBK(char **amp, char *strUtf8) //转码
{
   int len = MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)strUtf8, -1, NULL, 0);
   unsigned short * wszGBK = new unsigned short[len + 1];
   memset(wszGBK, 0, len * 2 + 2);
   MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)strUtf8, -1, (LPWSTR)wszGBK, len);
   len = WideCharToMultiByte(CP_ACP, 0, (LPCWSTR)wszGBK, -1, NULL, 0, NULL, NULL);
   //char *szGBK=new char[len + 1];
   *amp = new char[len + 1];
   memset(*amp, 0, len + 1);
   WideCharToMultiByte(CP_ACP, 0, (LPCWSTR)wszGBK, -1, *amp, len, NULL, NULL);
}

int main(int argc, char *argv[]) {
   TessBaseAPI *handle;
   PIX *img;
   char *text = NULL;
   //读取图片，原图像的路径
   if ((img = pixRead("test.jpg")) == NULL)
       die("Error reading image\n");

   handle = TessBaseAPICreate();
   //加载字库及设置语言
   if (TessBaseAPIInit3(handle,"./tessdata", "eng+chi_sim") != 0)
       die("Error initialising tesseract\n");

   //设置图片及识别
   TessBaseAPISetImage2(handle, img);
   if (TessBaseAPIRecognize(handle, NULL) != 0)
       die("Error in Tesseract recognition\n");

if ((text = TessBaseAPIGetUTF8Text(handle)) == NULL)
die("Error getting text\n");

   char *pResult = NULL;
   ConvertUtf8ToGBK(&pResult, text); //对结果转码
   cout << pResult << endl; //输出OCR识别的文本信息
   delete pResult;

   system("pause");
   TessDeleteText(text);
   TessBaseAPIEnd(handle);
   TessBaseAPIDelete(handle);
   pixDestroy(&img);

return 0;
}

VS2015+Tesseract4配置与示例（修改版）全套库类实例

相关推荐