How to use tesseract-ocr

使用动态库的调用方式：

1. Download tesseract-3.02.02-win32-lib-include-dirs  和leptonica-1.68-win32-lib-include-dirs from http://code.google.com/p/tesseract-ocr/downloads/list

2. 创建工程named TesseractSample 将tesseract-3.02.02-win32-lib-include-dirs里的include 和lib文件夹拷贝到TesseractSample下，将leptonica-1.68-win32-lib-include-dirs 内lib文件夹内的lept168d.lib 和liblept168d.dll 拷贝到TesseractSample工程lib文件夹下

3. 配置工程

项目->属性->c/c++->附加包含目录：..\include\tesseract

项目->属性->链接器->附加库目录：..\lib

代码：

#include "strngs.h"
#include "baseapi.h"
#pragma  comment(lib,"libtesseract302d.lib")

#include <iostream>
using namespace std;

#define FILEPATH	"F:\\TesseractSample\\Debug\\eng.bmp"
#define DIRPATH	"F:\\TesseractSample\\Debug"
//#define FILEPATH	"newpic.tif"
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,LPCWSTR(wszGBK), -1, NULL, 0, NULL, NULL);
	char *szGBK = new char[len + 1];
	memset(szGBK, 0, len + 1);
	WideCharToMultiByte(CP_ACP,0, LPCWSTR(wszGBK), -1, szGBK, len, NULL, NULL);
	//strUTF8 = szGBK;
	std::string strTemp(szGBK);
	delete[]szGBK;
	delete[]wszGBK;
	return strTemp;
}

int _tmain(int argc, _TCHAR* argv[])
{
	/*string tmp="";
	if(getenv("TESSDATA_PREFIX"))
	{
		tmp = getenv("TESSDATA_PREFIX");
	}*/
	
	tesseract::TessBaseAPI  api;  
	//DIRPATH 是程序的运行目录，如果将这个参数设置成null，那么需要设置环境变量TESSDATA_PREFIX
	api.Init(DIRPATH, "eng", tesseract::OEM_DEFAULT);  //init set lang chinese: chi_sim,English:eng

	STRING text_out;  
	if (!api.ProcessPages(FILEPATH, NULL, 0, &text_out))  
	{  
		return 0;  
	}  	
	cout<<text_out.string()<<endl;
	cout<<UTF8ToGBK(text_out.string()).c_str()<<endl;
	system("pause");
	return 0;
}