csharp:Optical Character Recognition
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Data;
using System.Drawing;
using System.IO;
using System.Drawing.Imaging;
using MODI;//Microsoft Office Document Imaging
// 首先用office安装盘这个组件,默认安装office的时候是不会安装的,只要添加这个组件功能就好了安装说明:http://support.microsoft.com/kb/982760
//组件Microsoft Office Document Imaging 12.0 Type Library(office2007)
//或者Microsoft Office Document Imaging 11.0 Type Library(office2003)
//中文简体OCR引擎 http://www.microsoft.com/downloads/thankyou.aspx?familyId=dd172063-9517-41d8-82af-29c38f7437b6&displayLang=zh-hk namespace ToText
{
/// <summary>
/// Optical Character Recognition光学字符识别
/// 20140507 Geovin Du
/// 涂聚文
/// </summary>
public static class OCRGetstring
{
/// <summary>
/// 语言类型
/// </summary>
/// <returns></returns>
public static DataTable getLanguageList()
{
DataTable dt = new DataTable();
dt.Columns.Add("ID",typeof(int));
dt.Columns.Add("LanguageName", typeof(string));
dt.Columns.Add("LanguageLCID", typeof(string));
//dt.Rows.Add(1, "", 1);
dt.Rows.Add(1,"简体中文", "2052");
dt.Rows.Add(2,"繁体中文", "1028");
dt.Rows.Add(3,"英语", "9");
dt.Rows.Add(4,"捷克语", "5");
dt.Rows.Add(5,"丹麦语", "6");
dt.Rows.Add(6,"德语", "7");
dt.Rows.Add(7,"希腊语", "8");
dt.Rows.Add(8,"西班牙语", "10");
dt.Rows.Add(9,"芬兰语", "11");
dt.Rows.Add(10,"法语", "12");
dt.Rows.Add(11, "匈牙利语", "14");
dt.Rows.Add(12, "意大利语", "16");
dt.Rows.Add(13, "日语", "17");
dt.Rows.Add(14, "韩语", "18");
dt.Rows.Add(15, "荷兰语", "19");
dt.Rows.Add(16, "挪威语", "20");
dt.Rows.Add(17, "波兰语", "21");
dt.Rows.Add(18, "葡萄牙语", "22");
dt.Rows.Add(19, "俄语", "25");
dt.Rows.Add(20,"瑞典语", "29");
dt.Rows.Add(21,"土耳其语", "31");
return dt;
} /// <summary>
///
/// </summary>
/// <param name="sValue"></param>
/// <returns></returns>
private static MODI.MiLANGUAGES GetLanuageType(string sValue)
{
switch (sValue)
{
case "2052":
return MODI.MiLANGUAGES.miLANG_CHINESE_SIMPLIFIED;
case "5":
return MODI.MiLANGUAGES.miLANG_CZECH;
case "6":
return MODI.MiLANGUAGES.miLANG_DANISH;
case "7":
return MODI.MiLANGUAGES.miLANG_GERMAN;
case "8":
return MODI.MiLANGUAGES.miLANG_GREEK;
case "9":
return MODI.MiLANGUAGES.miLANG_ENGLISH;
case "10":
return MODI.MiLANGUAGES.miLANG_SPANISH;
case "11":
return MODI.MiLANGUAGES.miLANG_FINNISH;
case "12":
return MODI.MiLANGUAGES.miLANG_FRENCH;
case "14":
return MODI.MiLANGUAGES.miLANG_HUNGARIAN;
case "16":
return MODI.MiLANGUAGES.miLANG_ITALIAN;
case "17":
return MODI.MiLANGUAGES.miLANG_JAPANESE;
case "18":
return MODI.MiLANGUAGES.miLANG_KOREAN;
case "19":
return MODI.MiLANGUAGES.miLANG_DUTCH;
case "20":
return MODI.MiLANGUAGES.miLANG_NORWEGIAN;
case "21":
return MODI.MiLANGUAGES.miLANG_POLISH;
case "22":
return MODI.MiLANGUAGES.miLANG_PORTUGUESE;
case "25":
return MODI.MiLANGUAGES.miLANG_RUSSIAN;
case "29":
return MODI.MiLANGUAGES.miLANG_SWEDISH;
case "31":
return MODI.MiLANGUAGES.miLANG_TURKISH;
case "1028":
return MODI.MiLANGUAGES.miLANG_CHINESE_TRADITIONAL;
default:
return MODI.MiLANGUAGES.miLANG_ENGLISH;
}
} /// <summary>
/// Images轉換文字
/// </summary>
/// <param name="image">Image</param>
/// <param name="language">语言类型</param>
/// <returns></returns>
public static string ExtractText(this System.Drawing.Image image,string language)
{
var tmpFile = Path.GetTempFileName();
StringBuilder sb = new StringBuilder();
//string text;
try
{
var bmp = new Bitmap(Math.Max(image.Width, 1024), Math.Max(image.Height, 768));
var gfxResize = Graphics.FromImage(bmp);
gfxResize.DrawImage(image, new Rectangle(0, 0, image.Width, image.Height));
bmp.Save(tmpFile + ".bmp", ImageFormat.Bmp);
var doc = new MODI.Document();
doc.Create(tmpFile + ".bmp");
// doc.OCR(MODI.MiLANGUAGES.miLANG_ENGLISH, true, true);
doc.OCR(GetLanuageType(language), true, true); // 识别文字类型
var img = (MODI.Image)doc.Images[0];
var layout = img.Layout;
sb.Append(layout.Text);
//text = sb.ToString();// layout.Text;
}
finally
{
File.Delete(tmpFile);
File.Delete(tmpFile + ".bmp");
} return sb.ToString();// text;
}
/// <summary>
/// 来源图片文件轉換文字
/// </summary>
/// <param name="fileToOCR">file文件</param>
/// <param name="language">语言类型</param>
/// <returns></returns>
public static string getFileToOCR(string fileToOCR, string language)
{
StringBuilder sb = new StringBuilder();
if (File.Exists(fileToOCR))
{ MODI.Document md = new MODI.Document();
md.Create(fileToOCR);
md.OCR(GetLanuageType(language), true, true);
MODI.Image img;
MODI.Layout layout;
for (int i = 0; i < md.Images.Count; i++)
{
img = (MODI.Image)md.Images[i];
layout = img.Layout;
sb.Append(layout.Text);
} md.Close(false); }
else
{
sb.Append("");
}
return sb.ToString();
}
}
}
csharp:Optical Character Recognition的更多相关文章
- OCR (Optical Character Recognition,光学字符识别)
OCR (Optical Character Recognition,光学字符识别)是指电子设备(例如扫描仪或数码相机)检查纸上打印的字符,通过检测暗.亮的模式确定其形状,然后用字符识别方法将形状翻译 ...
- 图片OCR(Optical Character Recognition)
目录 Photo OCR问题描述 滑动窗口(Sliding Windows) 获得大量数据和人工数据(Getting Logs of Data and Artificial Data) 瓶颈分析:需要 ...
- OCR(Optical Character Recognition)算法总结
https://zhuanlan.zhihu.com/p/84815144 最全OCR资料汇总,awesome-OCR
- 第 38 章 OCR - Optical Character Recognition
38.1. Tesseract 查找Tesseract安装包 $ apt-cache search Tesseract ocrodjvu - tool to perform OCR on DjVu d ...
- USACO 5.4 Character Recognition
Character Recognition This problem requires you to write a program that performs character recogniti ...
- USACO 5.4 Character Recognition(DP)
非常恶心的一题,卡了三个月,没什么动力做了,代码直接抄的别人的... 这题主要思路就是预处理出几个数组,再预处理出几个数组,最后DP,输出一下路径... 写起来挺非常麻烦,代码不贴了,丢人... 把U ...
- Go 语言相关的优秀框架,库及软件列表
If you see a package or project here that is no longer maintained or is not a good fit, please submi ...
- OCR 即 光学字符识别
OCR (Optical Character Recognition,光学字符识别)是指电子设备(例如扫描仪或数码相机)检查纸上打印的字符,通过检测暗.亮的模式确定其形状,然后用字符识别方法将形状翻译 ...
- Code Project精彩系列(转)
Code Project精彩系列(转) Code Project精彩系列(转) Applications Crafting a C# forms Editor From scratch htt ...
随机推荐
- nginx高性能WEB服务器系列之九--nginx运维故障日常解决方案
nginx系列友情链接:nginx高性能WEB服务器系列之一简介及安装https://www.cnblogs.com/maxtgood/p/9597596.htmlnginx高性能WEB服务器系列之二 ...
- JAVA JVM 杂谈(一)
JVM能够跨计算机体系结构来执行Java字节码,主要是由于JVM屏蔽了与各个计算机平台先关的软件或者硬件之间的差异,使得与平台先关的耦合统一由JVM的提供者来实现. JVM结构组成: 1.类加载器:在 ...
- 2016级算法第二次上机-F.ModricWang's Number Theory II
891 ModricWang's Number Theory II 思路 使得序列的最大公约数不为1,就是大于等于2,就是找到一个大于等于2的数,它能够整除序列中的所有数. 考虑使得一个数d整除数组中 ...
- jquery将json数据放入表格当中
数据: var datas = [{ name:"淘宝", url:"www.taobao.com", type:"购物网站" },{ na ...
- 论文阅读 | FoveaBox: Beyond Anchor-based Object Detector
论文阅读——FoveaBox: Beyond Anchor-based Object Detector 概述 这是一篇ArXiv 2019的文章,作者提出了一种新的anchor-free的目标检测框架 ...
- VS2013下使用cjson
想要在C++实现json文件的读取.因为中间也遇到过很简单的坑,为了增加记忆,对实现过程做一个记录. 本文采用的是静态链接库的方式: 1.先在github上下载源码, json源码下载地址 2.打开m ...
- (转)C++ main函数中参数argc和argv含义及用法
原博地址:https://blog.csdn.net/dcrmg/article/details/51987413 argc 是 argument count的缩写,表示传入main函数的参数个数: ...
- 关于DES加密内部收费版
数据加密算法(Data Encryption Algorithm,DEA)是一种对称加密算法,很可能是使用最广泛的密钥系统,特别是在保护金融数据的安全中,最初开发的DEA是嵌入硬件中的.通常,自动取款 ...
- 计算机网络c++实现截断二进制指数退避算法
#include<iostream> #include<vector> #include <stdio.h> #include<stdlib.h> // ...
- egg
简介 阿里的 红色的是项目名字 egg-init --type simple First && cd First egg-init --type simple Second &a ...