基于百度OCR的图片文字识别

时间:2022-12-05 23:26:33

  先上图,有图有真相

      基于百度OCR的图片文字识别

  首先在百度开通ORC服务,目前是免费的,普通识别每天50000次免费,非常棒!

       百度文档:http://ai.baidu.com/docs#/OCR-API/top

  下载百度SDK神马的就不多说了,需要包含CURL和JSON库,注意版本要求

  windows下的openssl 32位和64位一键安装包顺便分享下,自己安装太麻烦

  链接:https://pan.baidu.com/s/1HAuplB3deQGFk2eO8zC13A
  提取码:mh34 

  CURL和JSON库就不贴出来了,网上随便都能找到,需要的朋友可以找我,我私发给你。

  接下来进入正题,贴代码:

ImageRecogition.h

 1 #pragma once
 2 
 3 #include "json/json.h"
 4 
 5 class CImageRecogition
 6 {
 7 public:
 8     CImageRecogition();
 9     ~CImageRecogition();
10 
11 public:
12     /*accurate_basic*/
13     Json::Value static accurate_basic(std::string szFile);
14     /*general_basic*/
15     Json::Value static general_basic(std::string szFile);
16     /*general_enhanced*/
17     Json::Value static general_enhanced(std::string szFile);
18     /*receipt*/
19     Json::Value static receipt(std::string szFile);
20     /*custom*/
21     Json::Value static custom(std::string szFile);24     /*save result to file*/
25     void static SaveResultToFile(Json::Value & result, std::string szFile);
26 private:
27 };

ImageRecogition.cpp

#include "stdafx.h"
#include "ImageRecogition.h"

#include "baiduapi/ocr.h"

#define APP_ID        "xxxxxxx"
#define API_KEY        "xxxxxxx"
#define SECRET_KEY    "xxxxx"

CImageRecogition::CImageRecogition()
{

}

CImageRecogition::~CImageRecogition()
{

}

Json::Value CImageRecogition::accurate_basic(std::string szFile)
{
    aip::Ocr client(APP_ID, API_KEY, SECRET_KEY);

    std::string image;
    aip::get_file_content(szFile.c_str(), &image);
    std::map<std::string, std::string> options;
    options["detect_direction"] = "true";
    options["probability"] = "true";

    std::cout << "高精识别开始:";
    return client.accurate_basic(image, options);
}

Json::Value CImageRecogition::general_basic(std::string szFile)
{
    aip::Ocr client(APP_ID, API_KEY, SECRET_KEY);

    std::string image;
    aip::get_file_content(szFile.c_str(), &image);
    std::map<std::string, std::string> options;
    //options["language_type"] = "KOR";
    options["detect_direction"] = "true";
    options["detect_language"] = "true";
    options["probability"] = "true";

    std::cout << "普通识别开始:";
    return client.general_basic(image, options);
}

Json::Value CImageRecogition::general_enhanced(std::string szFile)
{
    aip::Ocr client(APP_ID, API_KEY, SECRET_KEY);

    std::string image;
    aip::get_file_content(szFile.c_str(), &image);
    std::map<std::string, std::string> options;
    //options["language_type"] = "KOR";
    options["detect_direction"] = "true";
    options["detect_language"] = "true";
    options["probability"] = "true";

    std::cout << "生僻字识别开始:";
    return client.general_enhanced(image, options);
}

Json::Value CImageRecogition::receipt(std::string szFile)
{
    aip::Ocr client(APP_ID, API_KEY, SECRET_KEY);

    std::string image;
    aip::get_file_content(szFile.c_str(), &image);
    std::map<std::string, std::string> options;
    //options["recognize_granularity"] = "small";
    options["probability"] = "true";
    //options["accuracy"] = "normal";
    options["detect_direction"] = "true";

    std::cout << "通用票据识别开始:";
    return client.receipt(image, options);
}

Json::Value CImageRecogition::custom(std::string szFile)
{
    aip::Ocr client(APP_ID, API_KEY, SECRET_KEY);

    std::string image;
    aip::get_file_content(szFile.c_str(), &image);
    std::map<std::string, std::string> options;
    std::string templateSign = "354b9b4fd9b0e4b38aedb8096260c6de";

    std::cout << "自定义模板识别开始:";
    return client.custom(image, templateSign, options);
}

void CImageRecogition::SaveResultToFile(Json::Value & result, std::string szFile)
{
    FILE* fp = nullptr;
    auto error_no = fopen_s(&fp, szFile.c_str(), "a+");
    if (fp != nullptr)
    {        
        fprintf_s(fp, "==============================================================================\n");
        SYSTEMTIME st;
        ::GetLocalTime(&st);
        fprintf_s(fp, "%04d-%02d-%02d %02d:%02d:%02d\n", st.wYear, st.wMonth, st.wDay, st.wHour, st.wMinute, st.wSecond);
        fprintf_s(fp, "log_id : %d\n", result["log_id"].asInt64());

        auto result_num = result["words_result"].size();

        if (result_num > 0)
            std::cout << "识别成功,识别行数:" << result_num << std::endl;
        else
            std::cout << "识别失败,未识别数据" << std::endl;

        for (int i = 0; i < result_num; ++i)
            fprintf_s(fp, "%s\n", result["words_result"][i]["words"].asString().c_str());

        fprintf_s(fp, "==============================================================================\n");
        fprintf_s(fp, "\n");
        fclose(fp);
    }
}
 

 然后就是main函数的调用了

#include "stdafx.h"
#include <iostream>

#include "ServiceLogic/ImageRecogition.h"
#include "curl/curl.h"
#include "DirFile/DirFile.h"

int _tmain(int argc, char* argv[])
{
    std::vector<std::string> vecFiles;
    DirFile::ListFiles(".", vecFiles, FILETYPE_JPG | FILETYPE_PNG | FILETYPE_JPEG);
    for (auto it : vecFiles)
    {
        std::cout << it << std::endl;
        std::string szFileName = it.substr(0, it.rfind("."));
        std::string szPath = "./Log_" + szFileName + "/";
        DirFile::CreatePath(szPath);

        //CImageRecogition::SaveResultToFile(CImageRecogition::accurate_basic(it), szPath + "accurate_basic.log");
        CImageRecogition::SaveResultToFile(CImageRecogition::general_basic(it), szPath + "general_basic.log");
        //CImageRecogition::SaveResultToFile(CImageRecogition::general_enhanced(it), szPath + "general_enhanced.log");
        //CImageRecogition::SaveResultToFile(CImageRecogition::receipt(it), szPath + "receipt.log");
        //CImageRecogition::SaveResultToFile(CImageRecogition::custom(it), szPath + "custom.log");
    }
    
    system("pause");
    return 0;
}

 

 DirFile.h是遍历当前目录下对应格式的文件,以及Log目录的创建的,这里就不贴出来了,毕竟不是这次的主题。

 百度ORC的识别率,对图片要求还是比较高的,本人给朝鲜族的朋友测试韩文的发票,效果还是挺差强人意的。看大家的需求吧。