Données OCR de mots et de caractères en C# (coordonnées, confiance, cadres de sélection)

using IronOcr;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("receipt.png");

var result = ocr.ReadDocumentAdvanced(input);

foreach (var word in result.Words)
{
    Console.WriteLine(
        $"Page {word.PageNumber} | " +
        $"Region {word.RegionIndex} | " +
        $"'{word.Text}' | " +
        $"Position: ({word.X}, {word.Y}) | " +
        $"Size: {word.Width}x{word.Height} | " +
        $"Confidence: {word.RegionConfidence:P1}"
    );
}

// ToString() override for diagnostic logging
Console.WriteLine(result.Words.First().ToString());

Imports IronOcr

Dim ocr As New IronTesseract()
Using input As New OcrInput()
    input.LoadImage("receipt.png")

    Dim result = ocr.ReadDocumentAdvanced(input)

    For Each word In result.Words
        Console.WriteLine(
            $"Page {word.PageNumber} | " &
            $"Region {word.RegionIndex} | " &
            $"'{word.Text}' | " &
            $"Position: ({word.X}, {word.Y}) | " &
            $"Size: {word.Width}x{word.Height} | " &
            $"Confidence: {word.RegionConfidence:P1}"
        )
    Next
End Using

' ToString() override for diagnostic logging
Console.WriteLine(result.Words.First().ToString())

using IronOcr;
using System.Linq;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("multi-column-doc.png");

var result = ocr.ReadDocumentAdvanced(input);

int targetPage = 1;
int lineThreshold = 10; // pixel tolerance for grouping same-line words

// Sort by line (Y), then left-to-right (X)
var pageWords = result.Words
    .Where(w => w.PageNumber == targetPage)
    .OrderBy(w => w.Y / lineThreshold)
    .ThenBy(w => w.X)
    .ToList();

foreach (var word in pageWords)
{
    Console.Write($"{word.Text} ");
}
Console.WriteLine();

Imports IronOcr
Imports System.Linq

Dim ocr As New IronTesseract()
Using input As New OcrInput()
    input.LoadImage("multi-column-doc.png")

    Dim result = ocr.ReadDocumentAdvanced(input)

    Dim targetPage As Integer = 1
    Dim lineThreshold As Integer = 10 ' pixel tolerance for grouping same-line words

    ' Sort by line (Y), then left-to-right (X)
    Dim pageWords = result.Words _
        .Where(Function(w) w.PageNumber = targetPage) _
        .OrderBy(Function(w) w.Y \ lineThreshold) _
        .ThenBy(Function(w) w.X) _
        .ToList()

    For Each word In pageWords
        Console.Write($"{word.Text} ")
    Next
    Console.WriteLine()
End Using

using IronOcr;
using System.Linq;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("noisy-scan.png");

var result = ocr.ReadDocumentAdvanced(input);

double threshold = 0.75;

var highConfidenceWords = result.Words
    .Where(w => w.RegionConfidence >= threshold)
    .ToList();

var lowConfidenceWords = result.Words
    .Where(w => w.RegionConfidence < threshold)
    .ToList();

Console.WriteLine($"Accepted: {highConfidenceWords.Count} words");
Console.WriteLine($"Rejected: {lowConfidenceWords.Count} words");

// Log rejected words for manual review
foreach (var word in lowConfidenceWords)
{
    Console.WriteLine(
        $"  LOW CONF: '{word.Text}' at ({word.X},{word.Y}) — {word.RegionConfidence:P1}"
    );
}

Imports IronOcr
Imports System.Linq

Dim ocr As New IronTesseract()
Using input As New OcrInput()
    input.LoadImage("noisy-scan.png")

    Dim result = ocr.ReadDocumentAdvanced(input)

    Dim threshold As Double = 0.75

    Dim highConfidenceWords = result.Words _
        .Where(Function(w) w.RegionConfidence >= threshold) _
        .ToList()

    Dim lowConfidenceWords = result.Words _
        .Where(Function(w) w.RegionConfidence < threshold) _
        .ToList()

    Console.WriteLine($"Accepted: {highConfidenceWords.Count} words")
    Console.WriteLine($"Rejected: {lowConfidenceWords.Count} words")

    ' Log rejected words for manual review
    For Each word In lowConfidenceWords
        Console.WriteLine(
            $"  LOW CONF: '{word.Text}' at ({word.X},{word.Y}) — {word.RegionConfidence:P1}"
        )
    Next
End Using

using IronOcr;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("form-field.png");

var result = ocr.ReadDocumentAdvanced(input);

foreach (var ch in result.Characters)
{
    Console.WriteLine(
        $"'{ch.Text}' | " +
        $"Box: ({ch.X}, {ch.Y}, {ch.Width}, {ch.Height}) | " +
        $"Page {ch.PageNumber}"
    );
}

// ToString() override provides diagnostic-friendly output
Console.WriteLine(result.Characters.First().ToString());

Imports IronOcr

Dim ocr = New IronTesseract()
Using input = New OcrInput()
    input.LoadImage("form-field.png")

    Dim result = ocr.ReadDocumentAdvanced(input)

    For Each ch In result.Characters
        Console.WriteLine($"'{ch.Text}' | Box: ({ch.X}, {ch.Y}, {ch.Width}, {ch.Height}) | Page {ch.PageNumber}")
    Next

    ' ToString() override provides diagnostic-friendly output
    Console.WriteLine(result.Characters.First().ToString())
End Using

using IronOcr;
using IronSoftware.Drawing;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("invoice.png");

var result = ocr.ReadDocumentAdvanced(input);

// Load the original image for cropping
var originalImage = AnyBitmap.FromFile("invoice.png");

// Find a specific word and crop its region
var targetWord = result.Words.FirstOrDefault(w => w.Text == "Total");
if (targetWord != null)
{
    Rectangle cropRect = targetWord.BoundingBox;
    AnyBitmap croppedRegion = originalImage.CropRegion(cropRect);
    croppedRegion.SaveAs("total-region.png");

    Console.WriteLine(
        $"Cropped '{targetWord.Text}' from " +
        $"({cropRect.X}, {cropRect.Y}, {cropRect.Width}, {cropRect.Height})"
    );
}

Imports IronOcr
Imports IronSoftware.Drawing

Dim ocr As New IronTesseract()
Using input As New OcrInput()
    input.LoadImage("invoice.png")

    Dim result = ocr.ReadDocumentAdvanced(input)

    ' Load the original image for cropping
    Dim originalImage = AnyBitmap.FromFile("invoice.png")

    ' Find a specific word and crop its region
    Dim targetWord = result.Words.FirstOrDefault(Function(w) w.Text = "Total")
    If targetWord IsNot Nothing Then
        Dim cropRect As Rectangle = targetWord.BoundingBox
        Dim croppedRegion As AnyBitmap = originalImage.CropRegion(cropRect)
        croppedRegion.SaveAs("total-region.png")

        Console.WriteLine(
            $"Cropped '{targetWord.Text}' from " &
            $"({cropRect.X}, {cropRect.Y}, {cropRect.Width}, {cropRect.Height})"
        )
    End If
End Using