如何在C＃项目中实现和执行OCR？

我已经搜索了一段时间以及所有我见过的OCR库请求。 我想知道如何实现最纯净，易于安装和使用OCR库以及安装到C＃项目的详细信息。

如果可行，我只想像通常的dll参考一样实现它…

例：

using org.pdfbox.pdmodel; using org.pdfbox.util; 

还有一个小的OCR代码示例会很好，例如：

 public string OCRFromBitmap(Bitmap Bmp) { Bmp.Save(temppath, System.Drawing.Imaging.ImageFormat.Tiff); string OcrResult = Analyze(temppath); File.Delete(temppath); return OcrResult; } 

所以请考虑我对OCR项目并不熟悉，并给我一个答案，比如跟假人说话。

编辑：我猜人们误解了我的要求。 我想知道如何将这些开源OCR库实现到C＃项目以及如何使用它们。 作为dup给出的链接没有给出我要求的答案。

Answer 1

这是一个:(查看http://hongouru.blogspot.ie/2011/09/c-ocr-optical-character-recognition.html或http://www.codeproject.com/Articles/41709/How-To-使用-Office-2007-OCR-Using-C获取更多信息）

 using MODI; static void Main(string[] args) { DocumentClass myDoc = new DocumentClass(); myDoc.Create(@"theDocumentName.tiff"); //we work with the .tiff extension myDoc.OCR(MiLANGUAGES.miLANG_ENGLISH, true, true); foreach (Image anImage in myDoc.Images) { Console.WriteLine(anImage.Layout.Text); //here we cout to the console. } } 

Answer 2

如果有人在研究这个，我一直在尝试不同的选择，以下方法会产生非常好的结果。 以下是获取工作示例的步骤：

1. 添加.NET Wrapper for tesseract到您的项目。 它可以通过NuGet包Install-Package Tesseract （ https://github.com/charlesw/tesseract ）添加。
2. 转到官方Tesseract项目的下载部分（ http://sofzh.miximages.com/c%23/文件复制到项目目录中，并将其设置为在构建时复制。
3. 在项目中创建以下两个文件（只是为了开始）：

Program.cs中

 using System; using Tesseract; using System.Diagnostics; namespace ConsoleApplication { class Program { public static void Main(string[] args) { var testImagePath = "./phototest.tif"; if (args.Length > 0) { testImagePath = args[0]; } try { var logger = new FormattedConsoleLogger(); var resultPrinter = new ResultPrinter(logger); using (var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default)) { using (var img = Pix.LoadFromFile(testImagePath)) { using (logger.Begin("Process image")) { var i = 1; using (var page = engine.Process(img)) { var text = page.GetText(); logger.Log("Text: {0}", text); logger.Log("Mean confidence: {0}", page.GetMeanConfidence()); using (var iter = page.GetIterator()) { iter.Begin(); do { if (i % 2 == 0) { using (logger.Begin("Line {0}", i)) { do { using (logger.Begin("Word Iteration")) { if (iter.IsAtBeginningOf(PageIteratorLevel.Block)) { logger.Log("New block"); } if (iter.IsAtBeginningOf(PageIteratorLevel.Para)) { logger.Log("New paragraph"); } if (iter.IsAtBeginningOf(PageIteratorLevel.TextLine)) { logger.Log("New line"); } logger.Log("word: " + iter.GetText(PageIteratorLevel.Word)); } } while (iter.Next(PageIteratorLevel.TextLine, PageIteratorLevel.Word)); } } i++; } while (iter.Next(PageIteratorLevel.Para, PageIteratorLevel.TextLine)); } } } } } } catch (Exception e) { Trace.TraceError(e.ToString()); Console.WriteLine("Unexpected Error: " + e.Message); Console.WriteLine("Details: "); Console.WriteLine(e.ToString()); } Console.Write("Press any key to continue . . . "); Console.ReadKey(true); } private class ResultPrinter { readonly FormattedConsoleLogger logger; public ResultPrinter(FormattedConsoleLogger logger) { this.logger = logger; } public void Print(ResultIterator iter) { logger.Log("Is beginning of block: {0}", iter.IsAtBeginningOf(PageIteratorLevel.Block)); logger.Log("Is beginning of para: {0}", iter.IsAtBeginningOf(PageIteratorLevel.Para)); logger.Log("Is beginning of text line: {0}", iter.IsAtBeginningOf(PageIteratorLevel.TextLine)); logger.Log("Is beginning of word: {0}", iter.IsAtBeginningOf(PageIteratorLevel.Word)); logger.Log("Is beginning of symbol: {0}", iter.IsAtBeginningOf(PageIteratorLevel.Symbol)); logger.Log("Block text: \"{0}\"", iter.GetText(PageIteratorLevel.Block)); logger.Log("Para text: \"{0}\"", iter.GetText(PageIteratorLevel.Para)); logger.Log("TextLine text: \"{0}\"", iter.GetText(PageIteratorLevel.TextLine)); logger.Log("Word text: \"{0}\"", iter.GetText(PageIteratorLevel.Word)); logger.Log("Symbol text: \"{0}\"", iter.GetText(PageIteratorLevel.Symbol)); } } } } 

FormattedConsoleLogger.cs

 using System; using System.Collections.Generic; using System.Text; using Tesseract; namespace ConsoleApplication { public class FormattedConsoleLogger { const string Tab = " "; private class Scope : DisposableBase { private int indentLevel; private string indent; private FormattedConsoleLogger container; public Scope(FormattedConsoleLogger container, int indentLevel) { this.container = container; this.indentLevel = indentLevel; StringBuilder indent = new StringBuilder(); for (int i = 0; i < indentLevel; i++) { indent.Append(Tab); } this.indent = indent.ToString(); } public void Log(string format, object[] args) { var message = String.Format(format, args); StringBuilder indentedMessage = new StringBuilder(message.Length + indent.Length * 10); int i = 0; bool isNewLine = true; while (i < message.Length) { if (message.Length > i && message[i] == '\r' && message[i + 1] == '\n') { indentedMessage.AppendLine(); isNewLine = true; i += 2; } else if (message[i] == '\r' || message[i] == '\n') { indentedMessage.AppendLine(); isNewLine = true; i++; } else { if (isNewLine) { indentedMessage.Append(indent); isNewLine = false; } indentedMessage.Append(message[i]); i++; } } Console.WriteLine(indentedMessage.ToString()); } public Scope Begin() { return new Scope(container, indentLevel + 1); } protected override void Dispose(bool disposing) { if (disposing) { var scope = container.scopes.Pop(); if (scope != this) { throw new InvalidOperationException("Format scope removed out of order."); } } } } private Stack scopes = new Stack(); public IDisposable Begin(string title = "", params object[] args) { Log(title, args); Scope scope; if (scopes.Count == 0) { scope = new Scope(this, 1); } else { scope = ActiveScope.Begin(); } scopes.Push(scope); return scope; } public void Log(string format, params object[] args) { if (scopes.Count > 0) { ActiveScope.Log(format, args); } else { Console.WriteLine(String.Format(format, args)); } } private Scope ActiveScope { get { var top = scopes.Peek(); if (top == null) throw new InvalidOperationException("No current scope"); return top; } } } } 

Answer 3

我正在使用带有TessNet2的tesseract OCR引擎（一个C＃包装器 – http://www.pixel-technology.com/freeware/tessnet2/ ）。

一些基本代码：

 using tessnet2; 

…

 Bitmap image = new Bitmap(@"u:\user files\bwalker\2849257.tif"); tessnet2.Tesseract ocr = new tessnet2.Tesseract(); ocr.SetVariable("tessedit_char_whitelist", "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz.,$-/#&=()\"':?"); // Accepted characters ocr.Init(@"C:\Users\bwalker\Documents\Visual Studio 2010\Projects\tessnetWinForms\tessnetWinForms\bin\Release\", "eng", false); // Directory of your tessdata folder List result = ocr.DoOCR(image, System.Drawing.Rectangle.Empty); string Results = ""; foreach (tessnet2.Word word in result) { Results += word.Confidence + ", " + word.Text + ", " + word.Left + ", " + word.Top + ", " + word.Bottom + ", " + word.Right + "\n"; } 

Answer 4

Tesseract 3.01有一个.NET包装器： https ： //github.com/charlesw/tesseract-ocr-dotnet

Answer 5

另一个选择是使用Neevia Document Converter，它具有内置的OCRfunction。 您可以运行几乎任何文件类型，它将生成一个重要的大文本文档的pdf，然后您可以使用ITextSharper打开和搜索