在實際環境中測試
在生產環境中測試無浮水印。
在任何需要的地方都能運作。
using IronOcr;
string imageText = new IronTesseract().Read(@"images\image.png").Text;
Imports IronOcr
Private imageText As String = (New IronTesseract()).Read("images\image.png").Text
IronOCR 在自動檢測和讀取不完美掃描的圖像和 PDF 文件中的文本方面具有獨特的能力。IronTesseract
類提供了最簡單的 API。
嘗試其他代碼樣本,以對您的 C# OCR 操作進行精細控制。
IronOCR 提供了目前在任何平台上最先進的 Tesseract 架構。具備更快的速度、更高的準確性以及原生 DLL 和 API。
支持 Tesseract 3、Tesseract 4 和 Tesseract 5 於 .NET 框架、標準、核心、Xamarin 和 Mono。
IronTesseract
使用直觀的API讀取
在 VB.NET 中執行 OCR 的方法using IronOcr;
using System;
var ocrTesseract = new IronTesseract();
ocrTesseract.Language = OcrLanguage.Arabic;
using (var ocrInput = new OcrInput())
{
ocrInput.LoadImage(@"images\arabic.gif");
var ocrResult = ocrTesseract.Read(ocrInput);
Console.WriteLine(ocrResult.Text);
}
// Example with a Custom Trained Font Being used:
var ocrTesseractCustomerLang = new IronTesseract();
ocrTesseractCustomerLang.UseCustomTesseractLanguageFile("custom_tesseract_files/custom.traineddata");
ocrTesseractCustomerLang.AddSecondaryLanguage(OcrLanguage.EnglishBest);
using (var ocrInput = new OcrInput())
{
ocrInput.LoadPdf(@"images\mixed-lang.pdf");
var ocrResult = ocrTesseractCustomerLang.Read(ocrInput);
Console.WriteLine(ocrResult.Text);
}
Imports IronOcr
Imports System
Private ocrTesseract = New IronTesseract()
ocrTesseract.Language = OcrLanguage.Arabic
Using ocrInput As New OcrInput()
ocrInput.LoadImage("images\arabic.gif")
Dim ocrResult = ocrTesseract.Read(ocrInput)
Console.WriteLine(ocrResult.Text)
End Using
' Example with a Custom Trained Font Being used:
Dim ocrTesseractCustomerLang = New IronTesseract()
ocrTesseractCustomerLang.UseCustomTesseractLanguageFile("custom_tesseract_files/custom.traineddata")
ocrTesseractCustomerLang.AddSecondaryLanguage(OcrLanguage.EnglishBest)
Using ocrInput As New OcrInput()
ocrInput.LoadPdf("images\mixed-lang.pdf")
Dim ocrResult = ocrTesseractCustomerLang.Read(ocrInput)
Console.WriteLine(ocrResult.Text)
End Using
IronOCR 支援 125 種國際語言。
除了預設安裝的英語外,語言包可通過 NuGet 或從我們的網站下載並添加到您的 .NET 專案中。 語言頁面大多數語言可以在快速,標準 (推薦) 和最佳品質。最佳可能更準確,但也較慢。
using IronOcr;
using IronSoftware.Drawing;
// We can delve deep into OCR results as an object model of
// Pages, Barcodes, Paragraphs, Lines, Words and Characters
// This allows us to explore, export and draw OCR content using other APIs/
var ocrTesseract = new IronTesseract();
ocrTesseract.Configuration.ReadBarCodes = true;
using var ocrInput = new OcrInput();
var pages = new int[] { 1, 2 };
ocrInput.LoadImageFrames("example.tiff", pages);
OcrResult ocrResult = ocrTesseract.Read(ocrInput);
foreach (var page in ocrResult.Pages)
{
// Page object
int PageNumber = page.PageNumber;
string PageText = page.Text;
int PageWordCount = page.WordCount;
// null if we dont set Ocr.Configuration.ReadBarCodes = true;
OcrResult.Barcode[] Barcodes = page.Barcodes;
AnyBitmap PageImage = page.ToBitmap(ocrInput);
int PageWidth = page.Width;
int PageHeight = page.Height;
double PageRotation = page.Rotation; // angular correction in degrees from OcrInput.Deskew()
foreach (var paragraph in page.Paragraphs)
{
// Pages -> Paragraphs
int ParagraphNumber = paragraph.ParagraphNumber;
string ParagraphText = paragraph.Text;
AnyBitmap ParagraphImage = paragraph.ToBitmap(ocrInput);
int ParagraphX_location = paragraph.X;
int ParagraphY_location = paragraph.Y;
int ParagraphWidth = paragraph.Width;
int ParagraphHeight = paragraph.Height;
double ParagraphOcrAccuracy = paragraph.Confidence;
OcrResult.TextFlow paragrapthText_direction = paragraph.TextDirection;
foreach (var line in paragraph.Lines)
{
// Pages -> Paragraphs -> Lines
int LineNumber = line.LineNumber;
string LineText = line.Text;
AnyBitmap LineImage = line.ToBitmap(ocrInput);
int LineX_location = line.X;
int LineY_location = line.Y;
int LineWidth = line.Width;
int LineHeight = line.Height;
double LineOcrAccuracy = line.Confidence;
double LineSkew = line.BaselineAngle;
double LineOffset = line.BaselineOffset;
foreach (var word in line.Words)
{
// Pages -> Paragraphs -> Lines -> Words
int WordNumber = word.WordNumber;
string WordText = word.Text;
AnyBitmap WordImage = word.ToBitmap(ocrInput);
int WordX_location = word.X;
int WordY_location = word.Y;
int WordWidth = word.Width;
int WordHeight = word.Height;
double WordOcrAccuracy = word.Confidence;
foreach (var character in word.Characters)
{
// Pages -> Paragraphs -> Lines -> Words -> Characters
int CharacterNumber = character.CharacterNumber;
string CharacterText = character.Text;
AnyBitmap CharacterImage = character.ToBitmap(ocrInput);
int CharacterX_location = character.X;
int CharacterY_location = character.Y;
int CharacterWidth = character.Width;
int CharacterHeight = character.Height;
double CharacterOcrAccuracy = character.Confidence;
// Output alternative symbols choices and their probability.
// Very useful for spellchecking
OcrResult.Choice[] Choices = character.Choices;
}
}
}
}
}
Imports IronOcr
Imports IronSoftware.Drawing
' We can delve deep into OCR results as an object model of
' Pages, Barcodes, Paragraphs, Lines, Words and Characters
' This allows us to explore, export and draw OCR content using other APIs/
Private ocrTesseract = New IronTesseract()
ocrTesseract.Configuration.ReadBarCodes = True
Dim ocrInput As New OcrInput()
Dim pages = New Integer() { 1, 2 }
ocrInput.LoadImageFrames("example.tiff", pages)
Dim ocrResult As OcrResult = ocrTesseract.Read(ocrInput)
For Each page In ocrResult.Pages
' Page object
Dim PageNumber As Integer = page.PageNumber
Dim PageText As String = page.Text
Dim PageWordCount As Integer = page.WordCount
' null if we dont set Ocr.Configuration.ReadBarCodes = true;
Dim Barcodes() As OcrResult.Barcode = page.Barcodes
Dim PageImage As AnyBitmap = page.ToBitmap(ocrInput)
Dim PageWidth As Integer = page.Width
Dim PageHeight As Integer = page.Height
Dim PageRotation As Double = page.Rotation ' angular correction in degrees from OcrInput.Deskew()
For Each paragraph In page.Paragraphs
' Pages -> Paragraphs
Dim ParagraphNumber As Integer = paragraph.ParagraphNumber
Dim ParagraphText As String = paragraph.Text
Dim ParagraphImage As AnyBitmap = paragraph.ToBitmap(ocrInput)
Dim ParagraphX_location As Integer = paragraph.X
Dim ParagraphY_location As Integer = paragraph.Y
Dim ParagraphWidth As Integer = paragraph.Width
Dim ParagraphHeight As Integer = paragraph.Height
Dim ParagraphOcrAccuracy As Double = paragraph.Confidence
Dim paragrapthText_direction As OcrResult.TextFlow = paragraph.TextDirection
For Each line In paragraph.Lines
' Pages -> Paragraphs -> Lines
Dim LineNumber As Integer = line.LineNumber
Dim LineText As String = line.Text
Dim LineImage As AnyBitmap = line.ToBitmap(ocrInput)
Dim LineX_location As Integer = line.X
Dim LineY_location As Integer = line.Y
Dim LineWidth As Integer = line.Width
Dim LineHeight As Integer = line.Height
Dim LineOcrAccuracy As Double = line.Confidence
Dim LineSkew As Double = line.BaselineAngle
Dim LineOffset As Double = line.BaselineOffset
For Each word In line.Words
' Pages -> Paragraphs -> Lines -> Words
Dim WordNumber As Integer = word.WordNumber
Dim WordText As String = word.Text
Dim WordImage As AnyBitmap = word.ToBitmap(ocrInput)
Dim WordX_location As Integer = word.X
Dim WordY_location As Integer = word.Y
Dim WordWidth As Integer = word.Width
Dim WordHeight As Integer = word.Height
Dim WordOcrAccuracy As Double = word.Confidence
For Each character In word.Characters
' Pages -> Paragraphs -> Lines -> Words -> Characters
Dim CharacterNumber As Integer = character.CharacterNumber
Dim CharacterText As String = character.Text
Dim CharacterImage As AnyBitmap = character.ToBitmap(ocrInput)
Dim CharacterX_location As Integer = character.X
Dim CharacterY_location As Integer = character.Y
Dim CharacterWidth As Integer = character.Width
Dim CharacterHeight As Integer = character.Height
Dim CharacterOcrAccuracy As Double = character.Confidence
' Output alternative symbols choices and their probability.
' Very useful for spellchecking
Dim Choices() As OcrResult.Choice = character.Choices
Next character
Next word
Next line
Next paragraph
Next page
IronOCR 透過使用 Tesseract 5 為每個掃描的頁面返回高級結果對象。這包含位置數據、圖像、文本、統計信心、替代符號選擇、字體名稱、字體大小裝飾、字體粗細和位置,分別為:
IronOCR真正特別之處在於它能夠讀取掃描效果不佳的文件。其獨特的預處理庫能夠減少背景雜訊、旋轉、變形和偏斜對齊,並簡化顏色和提高解析度及對比度。Iron 的 AutoOCR 和 Advanced OCR 設置為開發人員提供了每次都能達到最佳效果的工具。
了解更多IronOCR 將內容輸出為純文字和條碼數據。替代的結構化數據對象模型允許開發人員以結構化標題、段落、行、單詞和字符的格式接收所有內容,直接輸入到 .NET 應用程序中。
了解更多C# Tesseract 光學字符識別
Jim 一直是 IronOCR 開發方面的領導人物。Jim 設計並構建了影像處理算法及 OCR 閱讀方法。
觀看 Jim 的 Tesseract 比較C# 光學字符識別 ASP.NET
Iron 團隊在 .NET 軟體元件市場有超過 10 年的經驗。