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
- NOIP模拟赛
T1 1.聪明的小偷 (thief.pas/c/cpp) [问题描述] 从前有一个收藏家收藏了许多相同的硬币,并且将它们放在了n个排成一排的口袋里,每个口袋里都装了一定数量的硬币. 这些硬币价值不菲, ...
- 2016级算法第一次练习赛-F.AlvinZH的儿时梦想——机器人篇
864 AlvinZH的儿时梦想----机器人篇 题目链接:https://buaacoding.cn/problem/868/index 思路 中等题. 判断无限玩耍: \(p\) 的值能够承担的起 ...
- 40个迹象表明你还是PHP菜鸟
你是PHP菜鸟,如果你: 1. 不会利用如phpDoc这样的工具来恰当地注释你的代码2. 对优秀的集成开发环境如Zend Studio或Eclipse PDT视而不见3. 从未用过任何形式的版本控制系 ...
- Angular material mat-icon 资源参考_Images
ul,li>ol { margin-bottom: 0 } dt { font-weight: 700 } dd { margin: 0 1.5em 1.5em } img { height: ...
- flask开发笔记
目录 虚拟环境 Debug模式 配置文件 url传入参数 url反转 重定义向 模板 创建 jinjia2语法 模板继承 flash 加载静态文件 MySQL数据库命令 配置 更新.提交.删除 模型操 ...
- simulate UE activity
can: 1,connect, disconnect 2,configure serial,nic,com,model,version,IMEI,IMSI,IP 3,various AT comman ...
- 解决VS在高DPI下设计出的Winform程序界面变形问题
在目前高分屏流行的情况下,windows缩放与布局仍然设置为100%就显得太小(特别是笔记本),通常会调整为125%或150%, VS在缩放与布局设置为非100%的时候,就会自动启动DPI感知模式,以 ...
- CDH集群安装配置(七)--CDH组件的安装和配置
1. Clouder Manger页面的配置 访问主节点IP:(cdh1)192.168.80.81:7180 默认用户名和密码:admin,admin 选择一个版本 选择集群的服务器(agent), ...
- Protrator 官网和下载工具稍慢 , 但能使用. Angular CLI 内置 官方推荐 TS的 demo 不明显 , 而且依赖无法安装
npm uninstall -g protractor && cnpm install -g protractor && protractor --version 复 ...
- SPRING中的线程池ThreadPoolTaskExecutor(转)
转自:https://blog.csdn.net/zhanglongfei_test/article/details/51888433 一.初始化 1,直接调用 ThreadPoolTaskExecu ...