字符识别Google开源Tesseract-ocr的DLL调用方法

Tesseract-ocr的dll tesseract-3.02.02-win32-lib-include-dirs下载地址:
Google-Tesseract-OCR
      解压之后包括 include文件夹和Lib文件夹,配置头文件和库文件,建立工程进行测试。
#include "baseapi.h"
#include "strngs.h"

#pragma  comment(lib,"libtesseract302.lib")

char * str = "test.jpg";
tesseract::TessBaseAPI  api;  
api.Init(NULL, "chi_sim", tesseract::OEM_DEFAULT);  //初始化,设置语言包,中文简体:chi_sim;英文:eng;也可以自己训练语言包
//api.SetVariable( "tessedit_char_whitelist", "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz" );  
STRING text_out;  
if (!api.ProcessPages(str, NULL, 0, &text_out))  
{  
	return 0;  
}  

上边输出text_out.string(),结果为utf-8编码格式,因此需要转码,写了一个转成GBK的代码:

string UTF8ToGBK(const std::string& strUTF8)
{
	int len = MultiByteToWideChar(CP_UTF8, 0, strUTF8.c_str(), -1, NULL, 0);
	unsigned short * wszGBK = new unsigned short[len + 1];
	memset(wszGBK, 0, len * 2 + 2);
	MultiByteToWideChar(CP_UTF8, 0,LPCSTR(strUTF8.c_str()), -1, LPWSTR(wszGBK), len);

	len = WideCharToMultiByte(CP_ACP, 0,LPCTSTR(wszGBK), -1, NULL, 0, NULL, NULL);
	char *szGBK = new char[len + 1];
	memset(szGBK, 0, len + 1);
	WideCharToMultiByte(CP_ACP,0, LPCTSTR(wszGBK), -1, szGBK, len, NULL, NULL);
	//strUTF8 = szGBK;
	std::string strTemp(szGBK);
	delete[]szGBK;
	delete[]wszGBK;
	return strTemp;
}

由于是在mfc中应用,因此又写了一段mfc里边转成unicode的代码:

wchar_t * result_str;
CString result;
//utf-8转换成unicode
int len = MultiByteToWideChar(CP_UTF8,0,text_out.string(),-1,NULL,0);
result_str = new wchar_t[len + 1];
memset(result_str,0,len + 1);
MultiByteToWideChar(CP_UTF8,0,text_out.string(),-1,result_str,len);

//识别结果
result = result_str;


你可能感兴趣的:(C++,unicode,dll,utf-8,gbk,Tesseract-OCR)