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
- UIScrollView笔记
UIScrollView必须知道它的contentsize 这就是为啥TableView的row的height必须被计算,即使那些row还没有出现在屏幕. The scroll view must k ...
- uC/OS-II 函数之时间相关函数
获得更多资料欢迎进入我的网站或者 csdn或者博客园 对于有热心的小伙伴在微博上私信我,说我的uC/OS-II 一些函数简介篇幅有些过于长应该分开介绍.应小伙伴的要求,特此将文章分开进行讲解.上文主要 ...
- window phone8.1 hello,world(补交作业)
第一步,我们需要创建一个简单的hello,world程序来帮助我们了解大致的方向. 下面是这个小例子的步骤: 1.打开vs,点击 文件-新建-项目:如图:
- consul部署多台Docker集群
Consul 最近在学习Ocelot,发现里面集成Consul,所有部署一下多机版集群,后来发现网上都是在一台虚拟机中的Docker部署,而且大同小异,没有真正解释清楚. 前提准备 4台Centos虚 ...
- 前端统计图 echarts 实现简单柱状图
前端统计图 echarts实现简单柱状图 1. 引入 ECharts <!DOCTYPE html> <html> <head> <meta charse ...
- TensorFlow GPU 的使用
一.TensorFlow 设备分配 1.设备分配规则 If a TensorFlow operation has both CPU and GPU implementations, the GPU d ...
- Little Sub and Piggybank (杭师大第十二届校赛G题) DP
题目传送门 题意:每天能往存钱罐加任意实数的钱,每天不能多于起那一天放的钱数.如果某一天的钱数恰好等于那天的特价商品,则可以买,求最后的最大快乐值. 思路:先来一段来自出题人的题解: 显然的贪心:如果 ...
- 引入background和background-size不显示图片
.bgLeft { position: absolute; left: -95px; background: url("../images/logo_1.png") left to ...
- Python编程中报过的错
一.TypeError: not all arguments converted during string formatting def max(*args): print('max2:%s' % ...
- J15W-J45W全铜质截止阀厂家,J15W-J45W全铜质截止阀价格 - 专题栏目 - 无极资讯网
无极资讯网 首页 最新资讯 最新图集 最新标签 搜索 J15W-J45W全铜质截止阀 无极资讯网精心为您挑选了(J15W-J45W全铜质截止阀)信息,其中包含了(J15W-J45W全铜质截止阀)厂 ...