我已经搜索了一段时间，看到了一些OCR库的请求。我想知道如何在C#项目中实现最纯净、易于安装和使用的OCR库，并提供详细的安装信息。
如果可能的话，我只想像普通的DLL引用一样进行实现...
例子：
using org.pdfbox.pdmodel;
using org.pdfbox.util;
同时提供一小段OCR代码示例会更好，例如：
public string OCRFromBitmap(Bitmap Bmp)
{
Bmp.Save(temppath, System.Drawing.Imaging.ImageFormat.Tiff);
string OcrResult = Analyze(temppath);
File.Delete(temppath);
return OcrResult;
}
请注意，我对OCR项目不熟悉，请像向一个笨蛋一样给我答案。
编辑：我猜人们误解了我的请求。我想知道如何将这些开源OCR库实现到C#项目中以及如何使用它们。 给出的重复链接根本没有提供我所要求的答案。
Install-Package Tesseract（https://github.com/charlesw/tesseract）添加。tesseract-ocr-3.02.eng.tar.gz 英语语言数据，适用于Tesseract 3.02。tessdata目录，并将语言数据文件放入其中。属性并设置它们在构建时复制。System.Drawing的引用。Samples目录中将示例phototest.tif文件复制到您的项目目录中，并将其设置为在构建时复制。Program.cs
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<Scope> scopes = new Stack<Scope>();
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;
}
}
}
}
这里有一个：（查看http://hongouru.blogspot.ie/2011/09/c-ocr-optical-character-recognition.html 或者 http://www.codeproject.com/Articles/41709/How-To-Use-Office-2007-OCR-Using-C 获得更多信息）
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.
}
}
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<tessnet2.Word> 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";
}
GoogleCredential cred = GoogleCredential.FromJson(json);
Channel channel = new Channel(ImageAnnotatorClient.DefaultEndpoint.Host, ImageAnnotatorClient.DefaultEndpoint.Port, cred.ToChannelCredentials());
ImageAnnotatorClient client = ImageAnnotatorClient.Create(channel);
Image image = Image.FromStream(stream);
EntityAnnotation googleOcrText = client.DetectText(image).First();
Console.Write(googleOcrText.Description);
OCR.space 示例：
string uri = $"https://api.ocr.space/parse/imageurl?apikey=helloworld&url={imageUri}";
string responseString = WebUtilities.DoGetRequest(uri);
OcrSpaceResult result = JsonConvert.DeserializeObject<OcrSpaceResult>(responseString);
if ((!result.IsErroredOnProcessing) && !String.IsNullOrEmpty(result.ParsedResults[0].ParsedText))
return result.ParsedResults[0].ParsedText;
WinRT/UWP 有一个新的 API：OcrEngine.RecognizeAsync。它也可以在 WinForms 中使用：
...
//for AsBuffer
using System.Runtime.InteropServices.WindowsRuntime;
...
private async Task<SoftwareBitmap> loadSoftwareBitmap(string fn)
{
var sf= await StorageFile.GetFileFromPathAsync(fn);
SoftwareBitmap sb;
using (IRandomAccessStream stream = await sf.OpenAsync(FileAccessMode.Read))
{
BitmapDecoder decoder = await BitmapDecoder.CreateAsync(stream);
sb = await decoder.GetSoftwareBitmapAsync();
}
return sb;
}
async private void button5_Click(object sender, EventArgs e)
{
OcrEngine ocrEngine = null;
ocrEngine = OcrEngine.TryCreateFromUserProfileLanguages();
if (ocrEngine == null) return;
var fn = @"1.png";
var outputBitmap =await loadSoftwareBitmap(fn);
var ocrResult = await ocrEngine.RecognizeAsync(outputBitmap);
}
要在WinForms中使用WinRT/UWP API，请按照此处所述添加Nuget包“Microsoft.Windows.SDK.Contracts”（在此处测试了Win10 1803 SDK的版本为10.0.17134.100）。
编辑：以前的版本非常慢，大部分时间都用于图像和SoftwareBitmap之间的转换。新版本直接加载SoftwareBitmap，速度非常快。虽然它不能直接识别弯曲纸张上的字符（据我所知，许多其他框架也无法直接对弯曲纸张进行OCR），但结果非常好。