C#でマルチフレーム/ページTIFFとGIFからテキスト抽出・文字認識を行う方法

using IronOcr;

IronTesseract ocrTesseract = new IronTesseract();

// Import multi-page TIFF
using var imageInput = new OcrImageInput("multipage-document.tiff");

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

// Access results by page
foreach (var page in result.Pages)
{
    Console.WriteLine($"Page {page.PageNumber}:");
    Console.WriteLine(page.Text);
    Console.WriteLine("---");
}

Imports IronOcr

Dim ocrTesseract As New IronTesseract()

' Import multi-page TIFF
Using imageInput As New OcrImageInput("multipage-document.tiff")

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

    ' Access results by page
    For Each page In result.Pages
        Console.WriteLine($"Page {page.PageNumber}:")
        Console.WriteLine(page.Text)
        Console.WriteLine("---")
    Next
End Using

using IronOcr;
using System.Drawing;

// Configure OCR for individual frame processing
IronTesseract ocrTesseract = new IronTesseract();

// Load and split TIFF frames
using var multiFrameInput = new OcrImageInput("document.tiff");

// Process specific pages (0-indexed)
var pageIndices = new[] { 0, 2, 4 }; // Process pages 1, 3, and 5 only

foreach (int pageIndex in pageIndices)
{
    using var pageInput = new OcrImageInput("document.tiff", PageIndices: new[] { pageIndex });

    // Apply page-specific preprocessing if needed
    pageInput.DeNoise();
    pageInput.Deskew();

    var pageResult = ocrTesseract.Read(pageInput);
    Console.WriteLine($"Page {pageIndex + 1} text: {pageResult.Text}");
}

Imports IronOcr
Imports System.Drawing

' Configure OCR for individual frame processing
Dim ocrTesseract As New IronTesseract()

' Load and split TIFF frames
Using multiFrameInput As New OcrImageInput("document.tiff")

    ' Process specific pages (0-indexed)
    Dim pageIndices As Integer() = {0, 2, 4} ' Process pages 1, 3, and 5 only

    For Each pageIndex As Integer In pageIndices
        Using pageInput As New OcrImageInput("document.tiff", PageIndices:=New Integer() {pageIndex})

            ' Apply page-specific preprocessing if needed
            pageInput.DeNoise()
            pageInput.Deskew()

            Dim pageResult = ocrTesseract.Read(pageInput)
            Console.WriteLine($"Page {pageIndex + 1} text: {pageResult.Text}")
        End Using
    Next
End Using

using IronOcr;

IronTesseract ocrTesseract = new IronTesseract();

// Import GIF with preprocessing
using var imageInput = new OcrImageInput("low-quality.gif");

// Apply filters to improve quality
imageInput.ToGrayScale();      // Convert to grayscale
imageInput.Contrast(1.5);       // Increase contrast
imageInput.DeNoise();           // Remove noise
imageInput.EnhanceResolution(); // Upscale for better OCR

// Perform OCR with enhanced image
OcrResult result = ocrTesseract.Read(imageInput);

Imports IronOcr

Dim ocrTesseract As New IronTesseract()

' Import GIF with preprocessing
Using imageInput As New OcrImageInput("low-quality.gif")
    ' Apply filters to improve quality
    imageInput.ToGrayScale()      ' Convert to grayscale
    imageInput.Contrast(1.5)      ' Increase contrast
    imageInput.DeNoise()          ' Remove noise
    imageInput.EnhanceResolution() ' Upscale for better OCR

    ' Perform OCR with enhanced image
    Dim result As OcrResult = ocrTesseract.Read(imageInput)
End Using

using IronOcr;
using IronSoftware.Drawing;

// Define regions for form fields
var nameFieldRegion = new Rectangle(100, 50, 300, 40);
var dateFieldRegion = new Rectangle(100, 100, 200, 40);
var amountFieldRegion = new Rectangle(100, 150, 150, 40);

// Create OCR instance
IronTesseract ocr = new IronTesseract();

// Extract from each region
using var tiffInput = new OcrImageInput("form.tiff");

// Process each field
var name = ocr.Read(new OcrImageInput("form.tiff", ContentArea: nameFieldRegion)).Text.Trim();
var date = ocr.Read(new OcrImageInput("form.tiff", ContentArea: dateFieldRegion)).Text.Trim();
var amount = ocr.Read(new OcrImageInput("form.tiff", ContentArea: amountFieldRegion)).Text.Trim();

Console.WriteLine($"Name: {name}");
Console.WriteLine($"Date: {date}");
Console.WriteLine($"Amount: {amount}");

Imports IronOcr
Imports IronSoftware.Drawing

' Define regions for form fields
Dim nameFieldRegion As New Rectangle(100, 50, 300, 40)
Dim dateFieldRegion As New Rectangle(100, 100, 200, 40)
Dim amountFieldRegion As New Rectangle(100, 150, 150, 40)

' Create OCR instance
Dim ocr As New IronTesseract()

' Extract from each region
Using tiffInput As New OcrImageInput("form.tiff")
    ' Process each field
    Dim name As String = ocr.Read(New OcrImageInput("form.tiff", ContentArea:=nameFieldRegion)).Text.Trim()
    Dim date As String = ocr.Read(New OcrImageInput("form.tiff", ContentArea:=dateFieldRegion)).Text.Trim()
    Dim amount As String = ocr.Read(New OcrImageInput("form.tiff", ContentArea:=amountFieldRegion)).Text.Trim()

    Console.WriteLine($"Name: {name}")
    Console.WriteLine($"Date: {date}")
    Console.WriteLine($"Amount: {amount}")
End Using

using IronOcr;
using IronSoftware.Drawing;

// Test different regions to find optimal coordinates
var testRegions = new[] 
{ 
    new Rectangle(100, 100, 200, 50), 
    new Rectangle(100, 160, 200, 50), 
    new Rectangle(100, 220, 200, 50) 
};

IronTesseract ocr = new IronTesseract();

foreach (var region in testRegions)
{
    using var input = new OcrImageInput("document.tiff", ContentArea: region);
    var result = ocr.Read(input);

    // Save highlighted region for visual verification
    result.SaveAsHighlightedImage($"region_{region.X}_{region.Y}.png");
}

Imports IronOcr
Imports IronSoftware.Drawing

' Test different regions to find optimal coordinates
Dim testRegions = {
    New Rectangle(100, 100, 200, 50),
    New Rectangle(100, 160, 200, 50),
    New Rectangle(100, 220, 200, 50)
}

Dim ocr As New IronTesseract()

For Each region In testRegions
    Using input As New OcrImageInput("document.tiff", ContentArea:=region)
        Dim result = ocr.Read(input)

        ' Save highlighted region for visual verification
        result.SaveAsHighlightedImage($"region_{region.X}_{region.Y}.png")
    End Using
Next