OCR結果

獲得的不僅僅是文字。我們的API提供結構化資料，包含坐標、信心分數和完整的文件層次結構（頁面、行、單詞）。

資料輸出

文字

IronOCR以結構化物件和字串的形式返回段落、行、單詞和字元的文字輸出，使開發人員能夠快速存取和操作資料。

using IronOcr;

var ocrTesseract = new IronTesseract();
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 text
    string PageText = page.Text;
}

using IronOcr;

var ocrTesseract = new IronTesseract();
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 text
    string PageText = page.Text;
}

Imports IronOcr

Dim ocrTesseract As New IronTesseract()
Using ocrInput As New OcrInput()
    Dim pages As Integer() = {1, 2}
    ocrInput.LoadImageFrames("example.tiff", pages)
    Dim ocrResult As OcrResult = ocrTesseract.Read(ocrInput)
    For Each page In ocrResult.Pages
        ' Page text
        Dim PageText As String = page.Text
    Next
End Using

OCR文字位置

獲取每段落、行、單詞和字元的精確X/Y坐標和包圍框尺寸，使文字高亮顯示、區域OCR和資料驗證成為可能。

瞭解如何使用:在.NET C#中提取閱讀結果

using IronOcr;
using IronOcr.OcrResult;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Add image
using var imageInput = new OcrImageInput("sample.jpg");

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Retrieve list of detected paragraphs
Paragraph[] paragraphs = ocrResult.Paragraphs;

// Output Text location (X,Y) of the first paragraph
Console.WriteLine($"X: {paragraphs[0].X}");
Console.WriteLine($"Y: {paragraphs[0].Y}");

using IronOcr;
using IronOcr.OcrResult;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Add image
using var imageInput = new OcrImageInput("sample.jpg");

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Retrieve list of detected paragraphs
Paragraph[] paragraphs = ocrResult.Paragraphs;

// Output Text location (X,Y) of the first paragraph
Console.WriteLine($"X: {paragraphs[0].X}");
Console.WriteLine($"Y: {paragraphs[0].Y}");

Imports IronOcr
Imports IronOcr.OcrResult

' Instantiate IronTesseract
Dim ocrTesseract As New IronTesseract()

' Add image
Using imageInput As New OcrImageInput("sample.jpg")
    
    ' Perform OCR
    Dim ocrResult As OcrResult = ocrTesseract.Read(imageInput)
    
    ' Retrieve list of detected paragraphs
    Dim paragraphs() As Paragraph = ocrResult.Paragraphs
    
    ' Output Text location (X,Y) of the first paragraph
    Console.WriteLine($"X: {paragraphs(0).X}")
    Console.WriteLine($"Y: {paragraphs(0).Y}")
End Using

OCR輸出信心

接收提取文字的置信度分數。程式化地標記低信心結果供人工審核，以建立更可靠的自動化工作流。

瞭解如何使用:在.NET C#中獲得閱讀信心

using IronOcr;

var ocrTesseract = new IronTesseract();
using var ocrInput = new OcrInput();

// Load image from file
ocrInput.LoadImage("sameple.png");

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(ocrInput);

// Check Confidence level
Console.WriteLine($"Confidence: {ocrResult.Confidence}%");

using IronOcr;

var ocrTesseract = new IronTesseract();
using var ocrInput = new OcrInput();

// Load image from file
ocrInput.LoadImage("sameple.png");

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(ocrInput);

// Check Confidence level
Console.WriteLine($"Confidence: {ocrResult.Confidence}%");

Imports IronOcr

Dim ocrTesseract = New IronTesseract()
Using ocrInput = New OcrInput()

    ' Load image from file
    ocrInput.LoadImage("sameple.png")

    ' Perform OCR
    Dim ocrResult As OcrResult = ocrTesseract.Read(ocrInput)

    ' Check Confidence level
    Console.WriteLine($"Confidence: {ocrResult.Confidence}%")
End Using

OCR元素的圖像

除了文字外，還可以將從輸入文件中從OCR檢測到的文字的視覺元素匯出為單獨的圖像文件，這在存檔或處理非文字資料時非常有用。

瞭解如何使用:在.NET C#中提取閱讀結果

using IronOcr;
using IronSoftware.Drawing;

var ocrTesseract = new IronTesseract();
using var ocrInput = new OcrInput();
ocrInput.LoadImage("sample.png");
var ocrResult = ocrTesseract.Read(ocrInput);
foreach (var page in ocrResult.Pages)
{
    foreach (var word in page.Words)
    {
        word.ToBitmap(ocrInput).SaveAs($"page{page.PageNumber}_word{word.WordNumber}.png", AnyBitmap.ImageFormat.Png);
    }
}

using IronOcr;
using IronSoftware.Drawing;

var ocrTesseract = new IronTesseract();
using var ocrInput = new OcrInput();
ocrInput.LoadImage("sample.png");
var ocrResult = ocrTesseract.Read(ocrInput);
foreach (var page in ocrResult.Pages)
{
    foreach (var word in page.Words)
    {
        word.ToBitmap(ocrInput).SaveAs($"page{page.PageNumber}_word{word.WordNumber}.png", AnyBitmap.ImageFormat.Png);
    }
}

Imports IronOcr
Imports IronSoftware.Drawing

Dim ocrTesseract = New IronTesseract()
Using ocrInput = New OcrInput()
    ocrInput.LoadImage("sample.png")
    Dim ocrResult = ocrTesseract.Read(ocrInput)
    For Each page In ocrResult.Pages
        For Each word In page.Words
            word.ToBitmap(ocrInput).SaveAs($"page{page.PageNumber}_word{word.WordNumber}.png", AnyBitmap.ImageFormat.Png)
        Next
    Next
End Using

輸出型別

文字

使用結構化、層次化的API存取OCR結果。輕鬆從大段到單個字元進行導航，讓您對提取的文字及其元資料具有細粒度的控制。

瞭解如何使用:在.NET C#中提取閱讀結果

using IronOcr;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Add image
using var imageInput = new OcrImageInput("sample.jpg");

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Output the first detected paragraph text
Console.WriteLine($"Text: {ocrResult.Paragraphs[0].Text}");

using IronOcr;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Add image
using var imageInput = new OcrImageInput("sample.jpg");

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Output the first detected paragraph text
Console.WriteLine($"Text: {ocrResult.Paragraphs[0].Text}");

Imports IronOcr

' Instantiate IronTesseract
Dim ocrTesseract As New IronTesseract()

' Add image
Using imageInput As New OcrImageInput("sample.jpg")
    ' Perform OCR
    Dim ocrResult As OcrResult = ocrTesseract.Read(imageInput)
    
    ' Output the first detected paragraph text
    Console.WriteLine($"Text: {ocrResult.Paragraphs(0).Text}")
End Using

可搜尋的PDFs

將任何掃描文件或圖像轉換為全可搜尋的PDF文件。原始佈局被保留，但所有文字變得可選擇、可複製和可發現。

瞭解如何使用:將結果保存為可搜尋的PDF

using IronOcr;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Enable render as searchable PDF
ocrTesseract.Configuration.RenderSearchablePdf = true;

// Add image
using var imageInput = new OcrImageInput("sample.tiff");

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Export as searchable PDF
ocrResult.SaveAsSearchablePdf("searchablePdf.pdf");

using IronOcr;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Enable render as searchable PDF
ocrTesseract.Configuration.RenderSearchablePdf = true;

// Add image
using var imageInput = new OcrImageInput("sample.tiff");

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Export as searchable PDF
ocrResult.SaveAsSearchablePdf("searchablePdf.pdf");

Imports IronOcr

' Instantiate IronTesseract
Dim ocrTesseract As New IronTesseract()

' Enable render as searchable PDF
ocrTesseract.Configuration.RenderSearchablePdf = True

' Add image
Using imageInput As New OcrImageInput("sample.tiff")

    ' Perform OCR
    Dim ocrResult As OcrResult = ocrTesseract.Read(imageInput)

    ' Export as searchable PDF
    ocrResult.SaveAsSearchablePdf("searchablePdf.pdf")

End Using

hOCR

以hOCR格式導出結果，這是提供豐富元資料的HTML標準，包括每個單詞的文字、佈局資訊和坐標，非常適合進行高級文件分析。

瞭解如何使用:將結果保存為HTML文件中的hOCR

using IronOcr;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Enable render as hOCR
ocrTesseract.Configuration.RenderHocr = true;

// Add image
using var imageInput = new OcrImageInput("sample.tiff");
imageInput.Title = "Html Title";

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Export as HTML
ocrResult.SaveAsHocrFile("result.html");

using IronOcr;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Enable render as hOCR
ocrTesseract.Configuration.RenderHocr = true;

// Add image
using var imageInput = new OcrImageInput("sample.tiff");
imageInput.Title = "Html Title";

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Export as HTML
ocrResult.SaveAsHocrFile("result.html");

Imports IronOcr

' Instantiate IronTesseract
Dim ocrTesseract As New IronTesseract()

' Enable render as hOCR
ocrTesseract.Configuration.RenderHocr = True

' Add image
Using imageInput As New OcrImageInput("sample.tiff")
    imageInput.Title = "Html Title"

    ' Perform OCR
    Dim ocrResult As OcrResult = ocrTesseract.Read(imageInput)

    ' Export as HTML
    ocrResult.SaveAsHocrFile("result.html")
End Using

高亮文字為圖像

為了除錯和驗證，生成原始文件的圖像，所有識別文字均被突出顯示。這提供了OCR引擎精度和文字位置的快速視覺檢查。

瞭解如何使用:C#高亮文字以進行除錯

using IronOcr;

IronTesseract ocrTesseract = new IronTesseract();
using var ocrInput = new OcrInput();
ocrInput.LoadPdf("sample.pdf");
ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_page_", ResultHighlightType.Paragraph);

using IronOcr;

IronTesseract ocrTesseract = new IronTesseract();
using var ocrInput = new OcrInput();
ocrInput.LoadPdf("sample.pdf");
ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_page_", ResultHighlightType.Paragraph);

Imports IronOcr

Dim ocrTesseract As New IronTesseract()
Using ocrInput As New OcrInput()
    ocrInput.LoadPdf("sample.pdf")
    ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_page_", ResultHighlightType.Paragraph)
End Using

條碼和QR碼值

從文件中找到的任何條碼或QR碼中提取解碼的字串值。 API將此資料與文字結果一起提供，以提供完整的資料捕獲解決方案。

瞭解如何使用:在.NET C#中提取閱讀結果

using IronOcr;
using IronOcr.OcrResult;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Enable barcodes detection
ocrTesseract.Configuration.ReadBarCodes = true;

// Load PDF file
using OcrInput ocrInput = new OcrInput();
ocrInput.LoadPdf("sample.pdf");

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(ocrInput);

// Output Barcode value
Console.WriteLine(ocrResult.Barcodes[0].Value);

using IronOcr;
using IronOcr.OcrResult;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Enable barcodes detection
ocrTesseract.Configuration.ReadBarCodes = true;

// Load PDF file
using OcrInput ocrInput = new OcrInput();
ocrInput.LoadPdf("sample.pdf");

// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(ocrInput);

// Output Barcode value
Console.WriteLine(ocrResult.Barcodes[0].Value);

Imports IronOcr
Imports IronOcr.OcrResult

' Instantiate IronTesseract
Dim ocrTesseract As New IronTesseract()

' Enable barcodes detection
ocrTesseract.Configuration.ReadBarCodes = True

' Load PDF file
Using ocrInput As New OcrInput()
    ocrInput.LoadPdf("sample.pdf")

    ' Perform OCR
    Dim ocrResult As OcrResult = ocrTesseract.Read(ocrInput)

    ' Output Barcode value
    Console.WriteLine(ocrResult.Barcodes(0).Value)
End Using