在生產環境中無水印測試。
無論您需要它在哪裡運作都可以。
取得30天的完全功能產品。
幾分鐘內即可上手並運行。
在您的產品試用期間,獲得完整的工程師支援
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
Install-Package IronOcr
IronOCR支援 125 種國際語言。 除了預設安裝的英文之外,還可以透過NuGet將其他語言套件新增至您的.NET專案中,或從我們的語言頁面下載其他語言套件。 大多數語言都提供快速、標準(建議)和最佳品質三種版本。 最佳品質選項可能提供更準確的結果,但處理時間也會更慢。IronOCR語言支持
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);
double PageWidth = page.Width;
double 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 Double = page.Width
Dim PageHeight As Double = 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
Install-Package IronOcr
IronOCR使用 Tesseract 5 掃描每一頁,並傳回一個進階結果物件。 這包含位置資料、圖像、文字、統計置信度、替代符號、字體名稱、字號裝飾、字重以及每個元素的位置:
Page Paragraph WordBarcode
無論是護照頁面、發票、銀行對賬單、郵件、名片還是收據;光學字符識別 (OCR) 是一個基於模式識別、計算機視覺和機器學習的研究領域。公司利用 OCR 跨部門地從會計和金融系統、業務數字化、企業內容管理和數據報告系統中提取文本。
此外還構建其他成功案例。IronOCR 為 Google Tesseract 和 Microsoft 2021 Azure 認知服務增值,提供 IronOCR - 一個原生 C# OCR 庫。
如果您希望將真實的圖片轉換為 99% 的準確度,請繼續閱讀,看看 IronOCR 如何讓您構建一個高效、準確、可擴展、幾乎如人般的光學字符識別應用程序。
光學字符識別 (OCR) 被認為是一種被解決的現象,由於不同的 API 在保護方面表現出巨大的信心。然而,許多產品通常僵硬且不準確,無法在現實世界中應用。同樣,Tesseract OCR 適用於機器打印、高清晰度、完美的文本。
聽起來不錯?
但真正的世界並不總是擁有完美印刷和書寫的高分辨率文本。相反,旋轉、扭曲、低 DPI、背景噪音和所有數字瑕疵的是由 IronOCR 處理,包括從圖像文件中提取手寫文本。我們能夠確保 99.8 - 100% 準確、可搜尋的文檔,支持多平台,包括 Windows、Linux、macOS、Microsoft Azure、AWS 和 Docker - 這就是為什麼 C# 開發者選擇IronOCR 而非(基礎)Tesseract OCR - 一切都是關於增值。
裝備最好的工具!
除了以上功能,IronOCR 還使您能夠迅速處理圖像文檔。如果這還不夠,IronOCR API 的功能還包括以下內容:
從原生 .dll 或 exes 安裝轉變為單一的事實來源 —— 使用簡單的 C# API 開發一個原生 .NET 組件庫,支持:
IronOCR API 的藝術不僅限於此;您可以繼續探索我們的技術優勢功能。我們通過開發可靠的解決方案來簡化文件處理應用程式,從而減少商業複雜性,並通過提供行業領先功能來最大化商業收入,已經嵌入:
我們的光學字符識別過程始於自動圖像預處理,以改善圖像文件,提高提取響應速度。IronOCR 為您的工作增值,因為它允許用戶將示例基礎圖像文件提取為最優版本。IronOCR 涵蓋所有基礎:
由於 IronOCR 服務在 300DPI(每英寸點數)的圖像文件上最佳運行,任何明顯超出 200-300 DPI 範圍的圖像將重新採樣以適合目標範圍。
這意味着將 600 DPI 圖像下採樣為 300 DPI 或將 100 DPI 圖像上採樣為 200 DPI,具有 99%的置信度。
由於 IronOCR 認知服務的設計是針對單色圖像運行的,因此任何彩色或灰度圖像將使用自適應二值化算法轉換為單色。
該算法比較區域內的像素密度,確定用於將像素轉換為單色的閾值。
IronOCR 尋找文本行和字符模式,自動校正和旋轉輸入圖像資源至所需的方向。
通過 IronOCR,圖像文件會自動分析噪聲的存在和數量。噪音基本上是掃描圖像上的“雜點”。我們的自適應算法然後根據噪音顆粒的大小移除噪音。
一旦樣本圖像文件被預處理,IronOCR 便將輸入圖像文件分解為不同的處理區域。
另一個準備階段是將參考圖像分解為不同的邏輯區域。IronOCR 首先使用空白和模式在圖像中定位文本和圖片;文本區域與圖像分開。
然後將其分區為區段、列和文本塊。識別出來的圖像和剩餘的非文本像素在文本識別過程中被排除在外,並包括在智能輸出中。然後 IronOCR 使用網格線和文本塊將文本區域標識為表格。
執行多個相互連接的步驟,將像素斑點轉換為用戶可搜索的單行文本。例如包含字符分割、自適應分類、字典參考和其他相關過程,這些過程促成了最佳提取文本。
使用 IronOCR API 服務,我們通過多個數據文件範例在多種語言中對我們的工具進行了測試,包括單字級別、符號準確性和 Microsoft Office 格式中的佈局保留。雖然某些參數是自動測試的;其他包括視覺檢查。
IronOCR 允許您跨平台添加 OCR 功能,使用多種輸入格式轉換為用户可搜索的純文本串。要提升生產力與 IronOCR,請通過我們的免費教程文檔開始使用,我們的教程將指引您使用 IronOCR。立即下載我們的 NuGet 包安裝程序,並通過免費試用密鑰探索或隨時連接 24/7 的個人支持。無論您的團隊規模如何,都可以使用我們的終身許可證來滿足您的需求。
查看許可證
C# Tesseract OCR
C# OCR ASP.NET
Iron 的團隊有超過 10 年的 .NET 軟件組件市場經驗。