How to Read MICR Cheque using IronOCR in C#

What Does a MICR Cheque Look Like?

What Information Does the MICR Line Contain?

Check Number: This number uniquely identifies the specific cheque from the account holder's checkbook. It serves as a clear reference for tracking individual payments and maintaining transaction records. In automated processing systems, the check number helps prevent duplicate processing and assists in reconciliation procedures.

Routing Number: This nine-digit code, enclosed by the ⑆ transit symbol, identifies the financial institution that holds the account. It's the first piece of information a clearinghouse uses to direct the cheque to the correct bank for payment. The routing number follows a specific format: the first four digits identify the Federal Reserve routing symbol, the next four identify the institution, and the final digit is a checksum for validation.

Account Number: This identifies the specific customer account from which funds will be drawn. Its length can vary between different banks, typically ranging from 10 to 12 digits. Banks may include internal codes or branch identifiers within the account number structure.

What Code Do I Need to Extract MICR Data?

:path=/static-assets/ocr/content-code-examples/how-to/read-micr-cheque.cs

using IronOcr;
using IronSoftware.Drawing;
using System;

// Create a new instance of IronTesseract for performing OCR operations
IronTesseract ocr = new IronTesseract();

// Set the OCR language to MICR to recognize magnetic ink characters
// Must have MICR (IronOcr.Languages.MICR) installed beforehand
ocr.Language = OcrLanguage.MICR;

// Specify the file path of the input image containing MICR text
using (var input = new OcrInput())
{
    // Specify the MICR of the image to focus on for OCR (coordinates in pixels)
    var contentArea = new Rectangle(x: 215, y: 482, width: 520, height: 20);
    input.LoadImage("micr.png", contentArea);

    // Optional: Save the cropped area for verification
    input.StampCropRectangleAndSaveAs(contentArea, Color.Aqua, "cropped.png");

    // Run the OCR engine to read the MICR text from the input image
    var result = ocr.Read(input);
    // Output the recognized text to the console
    Console.WriteLine(result.Text);

    // Transit number is the first 7 characters of the MICR string
    string transitNum = result.Text.Substring(0, 7);
    // Routing number starts from the 8th character and is 11 characters long
    string routingNum = result.Text.Substring(7, 11);
    // Account number starts from the 22nd character to the end of the string
    string accountNum = result.Text.Substring(22);
}

The code demonstrates the complete workflow for MICR cheque processing. Before running this code, ensure you've installed the MICR language pack via NuGet. The OcrInput class provides powerful methods for loading and preprocessing images, while the Rectangle parameter allows precise targeting of the MICR line location.

What Results Should I Expect?

The output above shows the three sections obtained from the MICR cheque: the transit number, the routing number, and the account number. Notice how the special MICR symbols are represented in the output—this is normal behavior as these symbols have specific Unicode representations that may appear differently in console output.

MICR OCR Results

The OcrResult object provides detailed information about the scan:

Text: The extracted text from OcrInput. This includes all characters and symbols from the MICR line, maintaining their original sequence.

Confidence: Indicates the statistical accuracy confidence of an average of every character, with one being the highest and zero being the lowest. For MICR reading, confidence levels above 0.9 are typical due to the standardized font design. Learn more about confidence tracking in OCR results.

Blocks, Paragraphs, Lines, and Words: The hierarchical structure of recognized text, which for MICR typically consists of a single line with multiple word segments separated by symbols.

Barcode Data: While processing MICR, IronOCR can simultaneously detect any barcodes or QR codes present on the check.

How Can I Verify the Correct OCR Region?

To ensure you've selected the correct coordinates for the MICR line, you can visualize the ContentArea you defined. A simple way to do this is to draw the rectangle on the input image and save it as a new file with StampCropRectangleAndSaveAs. This helps you debug and fine-tune the coordinates for optimal performance.

To find the coordinates for your Rectangle, use a simple image editor like MS Paint. Open your cheque image, hover your mouse over the top-left and bottom-right corners of the MICR line, and note the (x,y) pixel coordinates. You can then calculate the rectangle's properties: (x1, y1, width, height), where width = x2-x1 and height = y2-y1.

For more advanced region selection techniques, explore OCR region targeting and content areas with PDFs.

Here is the output image after drawing the specified bounding box on our example cheque.

Output

The light blue rectangle confirms that we have correctly isolated the MICR line for processing.

Performance Optimization Tips

When processing multiple checks, consider implementing multithreading for improved performance. IronOCR handles concurrent operations efficiently:

// Process multiple cheques in parallel
var chequeFiles = Directory.GetFiles("cheques/", "*.png");
Parallel.ForEach(chequeFiles, file =>
{
    using (var ocr = new IronTesseract { Language = OcrLanguage.MICR })
    using (var input = new OcrInput())
    {
        input.LoadImage(file, micrRegion);
        var result = ocr.Read(input);
        ProcessMicrData(result.Text);
    }
});

// Process multiple cheques in parallel
var chequeFiles = Directory.GetFiles("cheques/", "*.png");
Parallel.ForEach(chequeFiles, file =>
{
    using (var ocr = new IronTesseract { Language = OcrLanguage.MICR })
    using (var input = new OcrInput())
    {
        input.LoadImage(file, micrRegion);
        var result = ocr.Read(input);
        ProcessMicrData(result.Text);
    }
});

Common Troubleshooting Scenarios

Low Quality Scans: If you're working with poor quality check images, apply image preprocessing filters to enhance readability. The MICR font's distinctive shape helps maintain accuracy even with degraded images.

Incorrect Character Recognition: Ensure you have the latest MICR language pack installed. The specialized MICR language configuration is specifically trained for E-13B font recognition.

Variable MICR Line Positions: Different banks may position the MICR line at slightly different locations. Consider implementing dynamic region detection or maintaining a configuration file with coordinates for different check formats.

Related Financial Document Processing

IronOCR's capabilities extend beyond check processing. Explore these related features for comprehensive financial document automation:

• Extract data from scanned invoices
• Process identity documents for KYC compliance
• Read tables in financial statements

By mastering MICR reading with IronOCR, you've taken the first step toward fully automated financial document processing, reducing manual entry errors and accelerating your workflow significantly.