API zum Scannen von Belegen: Daten aus Belegen mit C# und IronOCR extrahieren

using IronOcr;
using System;
using System.Collections.Generic;
using System.Text.RegularExpressions;

class ReceiptScanner
{
    static void Main()
    {
        var ocr = new IronTesseract();

        // Configure OCR for optimal receipt reading
        ocr.Configuration.WhiteListCharacters = "0123456789.$,ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz% ";
        ocr.Configuration.BlackListCharacters = "~`@#*_}{][|\\";
        ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5;

        // Load the image of the receipt
        using (var input = new OcrInput(@"r2.png"))
        {
            // Apply image enhancement filters
            input.Deskew(); // Fix image rotation
            input.EnhanceResolution(225); // Optimal DPI for receipts
            input.DeNoise(); // Remove background noise
            input.Sharpen(); // Improve text clarity

            // Perform OCR on the input image
            var result = ocr.Read(input);

            // Regular expression patterns to extract relevant details from the OCR result
            var descriptionPattern = @"\w+\s+(.*?)\s+(\d+\.\d+)\s+Units\s+(\d+\.\d+)\s+Tax15%\s+\$(\d+\.\d+)";
            var pricePattern = @"\$\d+(\.\d{2})?";
            var datePattern = @"\d{1,2}[/-]\d{1,2}[/-]\d{2,4}";

            // Variables to store extracted data
            var descriptions = new List<string>();
            var unitPrices = new List<decimal>();
            var taxes = new List<decimal>();
            var amounts = new List<decimal>();

            var lines = result.Text.Split('\n');
            foreach (var line in lines)
            {
                // Match each line against the description pattern
                var descriptionMatch = Regex.Match(line, descriptionPattern);
                if (descriptionMatch.Success)
                {
                    descriptions.Add(descriptionMatch.Groups[1].Value.Trim());
                    unitPrices.Add(decimal.Parse(descriptionMatch.Groups[2].Value));

                    // Calculate tax and total amount for each item
                    var tax = unitPrices[unitPrices.Count - 1] * 0.15m;
                    taxes.Add(tax);
                    amounts.Add(unitPrices[unitPrices.Count - 1] + tax);
                }

                // Extract date if found
                var dateMatch = Regex.Match(line, datePattern);
                if (dateMatch.Success)
                {
                    Console.WriteLine($"Receipt Date: {dateMatch.Value}");
                }
            }

            // Output the extracted data
            for (int i = 0; i < descriptions.Count; i++)
            {
                Console.WriteLine($"Description: {descriptions[i]}");
                Console.WriteLine($"Quantity: 1.00 Units");
                Console.WriteLine($"Unit Price: ${unitPrices[i]:0.00}");
                Console.WriteLine($"Taxes: ${taxes[i]:0.00}");
                Console.WriteLine($"Amount: ${amounts[i]:0.00}");
                Console.WriteLine("-----------------------");
            }

            // Calculate and display totals
            var subtotal = unitPrices.Sum();
            var totalTax = taxes.Sum();
            var grandTotal = amounts.Sum();

            Console.WriteLine($"\nSubtotal: ${subtotal:0.00}");
            Console.WriteLine($"Total Tax: ${totalTax:0.00}");
            Console.WriteLine($"Grand Total: ${grandTotal:0.00}");
        }
    }
}

Imports IronOcr
Imports System
Imports System.Collections.Generic
Imports System.Text.RegularExpressions
Imports System.Linq

Class ReceiptScanner
    Shared Sub Main()
        Dim ocr = New IronTesseract()

        ' Configure OCR for optimal receipt reading
        ocr.Configuration.WhiteListCharacters = "0123456789.$,ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz% "
        ocr.Configuration.BlackListCharacters = "~`@#*_}{][|\"
        ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5

        ' Load the image of the receipt
        Using input = New OcrInput("r2.png")
            ' Apply image enhancement filters
            input.Deskew() ' Fix image rotation
            input.EnhanceResolution(225) ' Optimal DPI for receipts
            input.DeNoise() ' Remove background noise
            input.Sharpen() ' Improve text clarity

            ' Perform OCR on the input image
            Dim result = ocr.Read(input)

            ' Regular expression patterns to extract relevant details from the OCR result
            Dim descriptionPattern = "\w+\s+(.*?)\s+(\d+\.\d+)\s+Units\s+(\d+\.\d+)\s+Tax15%\s+\$(\d+\.\d+)"
            Dim pricePattern = "\$\d+(\.\d{2})?"
            Dim datePattern = "\d{1,2}[/-]\d{1,2}[/-]\d{2,4}"

            ' Variables to store extracted data
            Dim descriptions = New List(Of String)()
            Dim unitPrices = New List(Of Decimal)()
            Dim taxes = New List(Of Decimal)()
            Dim amounts = New List(Of Decimal)()

            Dim lines = result.Text.Split(ControlChars.Lf)
            For Each line In lines
                ' Match each line against the description pattern
                Dim descriptionMatch = Regex.Match(line, descriptionPattern)
                If descriptionMatch.Success Then
                    descriptions.Add(descriptionMatch.Groups(1).Value.Trim())
                    unitPrices.Add(Decimal.Parse(descriptionMatch.Groups(2).Value))

                    ' Calculate tax and total amount for each item
                    Dim tax = unitPrices(unitPrices.Count - 1) * 0.15D
                    taxes.Add(tax)
                    amounts.Add(unitPrices(unitPrices.Count - 1) + tax)
                End If

                ' Extract date if found
                Dim dateMatch = Regex.Match(line, datePattern)
                If dateMatch.Success Then
                    Console.WriteLine($"Receipt Date: {dateMatch.Value}")
                End If
            Next

            ' Output the extracted data
            For i As Integer = 0 To descriptions.Count - 1
                Console.WriteLine($"Description: {descriptions(i)}")
                Console.WriteLine("Quantity: 1.00 Units")
                Console.WriteLine($"Unit Price: ${unitPrices(i):0.00}")
                Console.WriteLine($"Taxes: ${taxes(i):0.00}")
                Console.WriteLine($"Amount: ${amounts(i):0.00}")
                Console.WriteLine("-----------------------")
            Next

            ' Calculate and display totals
            Dim subtotal = unitPrices.Sum()
            Dim totalTax = taxes.Sum()
            Dim grandTotal = amounts.Sum()

            Console.WriteLine(vbCrLf & $"Subtotal: ${subtotal:0.00}")
            Console.WriteLine($"Total Tax: ${totalTax:0.00}")
            Console.WriteLine($"Grand Total: ${grandTotal:0.00}")
        End Using
    End Sub
End Class

using IronOcr;
using System;
using System.Collections.Generic;
using System.Linq;

class ReceiptLayoutHandler
{
    static void Main()
    {
        var ocr = new IronTesseract();

        // Configure for different receipt layouts
        ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd;
        ocr.Configuration.EngineMode = TesseractEngineMode.TesseractAndLstm;

        using (var input = new OcrInput(@"complex_receipt.jpg"))
        {
            // Apply region-specific processing
            var cropRegion = new CropRectangle(x: 0, y: 100, width: 400, height: 800);
            input.AddImage(@"complex_receipt.jpg", cropRegion);

            // Process with confidence tracking
            var result = ocr.Read(input);

            // Parse using confidence scores
            var highConfidenceLines = result.Lines
                .Where(line => line.Confidence > 85)
                .Select(line => line.Text)
                .ToList();

            // Extract data with fallback strategies
            var total = ExtractTotal(highConfidenceLines) 
                        ?? ExtractTotalAlternative(result.Text);

            Console.WriteLine($"Receipt Total: {total}");
        }
    }

    static decimal? ExtractTotal(List<string> lines)
    {
        // Primary extraction method
        foreach (var line in lines)
        {
            if (line.Contains("TOTAL") && 
                System.Text.RegularExpressions.Regex.IsMatch(line, @"\d+\.\d{2}"))
            {
                var match = System.Text.RegularExpressions.Regex.Match(line, @"(\d+\.\d{2})");
                if (decimal.TryParse(match.Value, out var total))
                    return total;
            }
        }
        return null;
    }

    static decimal? ExtractTotalAlternative(string fullText)
    {
        // Fallback extraction method
        var pattern = @"(?:Total|TOTAL|Grand Total|Amount Due).*?(\d+\.\d{2})";
        var match = System.Text.RegularExpressions.Regex.Match(fullText, pattern);

        if (match.Success && decimal.TryParse(match.Groups[1].Value, out var total))
            return total;

        return null;
    }
}

Imports IronOcr
Imports System
Imports System.Collections.Generic
Imports System.Linq

Class ReceiptLayoutHandler
    Shared Sub Main()
        Dim ocr = New IronTesseract()

        ' Configure for different receipt layouts
        ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd
        ocr.Configuration.EngineMode = TesseractEngineMode.TesseractAndLstm

        Using input = New OcrInput("complex_receipt.jpg")
            ' Apply region-specific processing
            Dim cropRegion = New CropRectangle(x:=0, y:=100, width:=400, height:=800)
            input.AddImage("complex_receipt.jpg", cropRegion)

            ' Process with confidence tracking
            Dim result = ocr.Read(input)

            ' Parse using confidence scores
            Dim highConfidenceLines = result.Lines _
                .Where(Function(line) line.Confidence > 85) _
                .Select(Function(line) line.Text) _
                .ToList()

            ' Extract data with fallback strategies
            Dim total = ExtractTotal(highConfidenceLines) _
                        OrElse ExtractTotalAlternative(result.Text)

            Console.WriteLine($"Receipt Total: {total}")
        End Using
    End Sub

    Shared Function ExtractTotal(lines As List(Of String)) As Decimal?
        ' Primary extraction method
        For Each line In lines
            If line.Contains("TOTAL") AndAlso _
                System.Text.RegularExpressions.Regex.IsMatch(line, "\d+\.\d{2}") Then
                Dim match = System.Text.RegularExpressions.Regex.Match(line, "(\d+\.\d{2})")
                Dim total As Decimal
                If Decimal.TryParse(match.Value, total) Then
                    Return total
                End If
            End If
        Next
        Return Nothing
    End Function

    Shared Function ExtractTotalAlternative(fullText As String) As Decimal?
        ' Fallback extraction method
        Dim pattern = "(?:Total|TOTAL|Grand Total|Amount Due).*?(\d+\.\d{2})"
        Dim match = System.Text.RegularExpressions.Regex.Match(fullText, pattern)

        Dim total As Decimal
        If match.Success AndAlso Decimal.TryParse(match.Groups(1).Value, total) Then
            Return total
        End If

        Return Nothing
    End Function
End Class