OCR 结果

获取的不仅仅是文本。我们的 API 提供结构化数据，包括坐标、置信度分数和完整的文档层次结构（页、行、字）。

数据输出

文本

IronOCR 将段落、行、单词和字符的文本输出以结构化对象和字符串的形式返回，使开发人员能够快速访问和操作数据。

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 文本位置

获取每个段落、行、单词和字符的精确 X/Y 坐标和边界框尺寸，实现文本高亮显示、区域 OCR 和数据验证。

了解如何：在 .NET C# 中提取读取结果

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 输出信心

对提取的文本进行置信度评分。以编程方式标记低置信度结果，供人工审核，以建立更可靠的自动化工作流程。

了解如何：在.NET C#中获得阅读信心

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 元素的图像

除文本外，还可将输入文档中通过 OCR 检测到的文本视觉元素导出为单独的图像文件，这对归档或处理非文本数据非常有用。

了解如何：在 .NET C# 中提取读取结果

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

输出类型

文本

通过结构化、分级式 API 访问 OCR 结果。从大段落轻松浏览到单个字符，让您对提取的文本及其元数据进行细粒度控制。

了解如何：在 .NET C# 中提取读取结果

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

可搜索的 PDFs

将任何扫描文件或图像转换成完全可搜索的 PDF 文件。保留原始布局，但所有文本均可选择、复制和查找。

了解如何：将结果保存为可搜索的 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 格式导出结果，这是一种基于 HTML 的标准，可提供丰富的元数据，包括文本、布局信息和每个单词的坐标，非常适合高级文档分析。

了解如何：在 HTML 文件中将结果保存为 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

将文本突出显示为图像

为了进行调试和验证，应生成原始文档的图像，并突出显示所有已识别的文本。这样可以快速直观地检查 OCR 引擎的准确性和文本位置。

了解如何：C# 高亮显示文本以进行调试

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

条形码和 QR 码值

从文档中发现的任何 BarCode 或 QR 码中提取解码字符串值。API 在提供文本结果的同时提供这些数据，从而提供完整的数据采集解决方案。

了解如何：在 .NET C# 中提取读取结果

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