using IronOcr; using IronSoftware.Drawing; // We can delve deep into OCR results as an object model of // Pages, Barcodes, Paragraphs, Lines, Words and Characters // This allows us to explore, export and draw OCR content using other APIs/ var ocrTesseract = new IronTesseract(); ocrTesseract.Configuration.ReadBarCodes = true; 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 object int PageNumber = page.PageNumber; string PageText = page.Text; int PageWordCount = page.WordCount; // null if we dont set Ocr.Configuration.ReadBarCodes = true; OcrResult.Barcode[] Barcodes = page.Barcodes; AnyBitmap PageImage = page.ToBitmap(ocrInput); int PageWidth = page.Width; int PageHeight = page.Height; double PageRotation = page.Rotation; // angular correction in degrees from OcrInput.Deskew() foreach (var paragraph in page.Paragraphs) { // Pages -> Paragraphs int ParagraphNumber = paragraph.ParagraphNumber; string ParagraphText = paragraph.Text; AnyBitmap ParagraphImage = paragraph.ToBitmap(ocrInput); int ParagraphX_location = paragraph.X; int ParagraphY_location = paragraph.Y; int ParagraphWidth = paragraph.Width; int ParagraphHeight = paragraph.Height; double ParagraphOcrAccuracy = paragraph.Confidence; OcrResult.TextFlow paragrapthText_direction = paragraph.TextDirection; foreach (var line in paragraph.Lines) { // Pages -> Paragraphs -> Lines int LineNumber = line.LineNumber; string LineText = line.Text; AnyBitmap LineImage = line.ToBitmap(ocrInput); int LineX_location = line.X; int LineY_location = line.Y; int LineWidth = line.Width; int LineHeight = line.Height; double LineOcrAccuracy = line.Confidence; double LineSkew = line.BaselineAngle; double LineOffset = line.BaselineOffset; foreach (var word in line.Words) { // Pages -> Paragraphs -> Lines -> Words int WordNumber = word.WordNumber; string WordText = word.Text; AnyBitmap WordImage = word.ToBitmap(ocrInput); int WordX_location = word.X; int WordY_location = word.Y; int WordWidth = word.Width; int WordHeight = word.Height; double WordOcrAccuracy = word.Confidence; foreach (var character in word.Characters) { // Pages -> Paragraphs -> Lines -> Words -> Characters int CharacterNumber = character.CharacterNumber; string CharacterText = character.Text; AnyBitmap CharacterImage = character.ToBitmap(ocrInput); int CharacterX_location = character.X; int CharacterY_location = character.Y; int CharacterWidth = character.Width; int CharacterHeight = character.Height; double CharacterOcrAccuracy = character.Confidence; // Output alternative symbols choices and their probability. // Very useful for spellchecking OcrResult.Choice[] Choices = character.Choices; } } } } }

Published February 19, 2024

Invoice OCR Open Source (Free & Paid Tools Comparison)

Introduction

Optical Character Recognition (OCR) is now the most important technology for document processing like invoices. It has evolved in every aspect of business, from education to the industry level. Everywhere, you can see the usage of OCR software because it decreases the use of manual data entry. There are many types of Invoice OCR API that developers can use to build OCR software applications to process invoices.

In this article, we'll explore the three C# Invoice OCR Open Source software and libraries for Invoice processing and other OCR processes. We'll discuss the IronOCR, too (separate from them), which is the best-paid option for developers to integrate advanced OCR capabilities in C# projects. Let's get started with open-source options.

Tesseract OCR

Tesseract OCR, initially developed by Hewlett Packard and now maintained by Google, stands as a powerful open-source OCR engine. It's capable of reading a wide range of document types and converting them into usable data. It supports multiple languages, making it a valuable resource for global businesses.

C# developers find Tesseract OCR exceptionally useful due to its versatility and extraction accuracy. By incorporating Tesseract into their software applications, developers can efficiently process new invoices and extract data and relevant information such as purchase orders and tax amounts. We can use the extracted data to extract the invoice number and items from the PDF invoice.

Capabilities and Features of Tesseract OCR in C#

Integration in .NET Applications: In C# projects, integrating Tesseract OCR involves leveraging the Tesseract .NET SDK or wrapper, which provides a streamlined way to incorporate OCR functionalities. The integration allows developers to work within the .NET environment they are familiar with, ensuring a smooth development process.

Text Recognition: Tesseract OCR excels in recognizing and extracting text from various image formats. It's adept at handling a range of document types, from scanned documents and PDF files to images captured in different lighting conditions or angles.

Support for Multiple Languages: One of the significant strengths of Tesseract is its support for over 100 languages. This makes it an incredibly versatile tool for global applications that need to process and analyze text data from diverse linguistic sources.

Customization and Training: Tesseract allows developers to train the engine with new fonts and languages, offering a tailored OCR solution that suits specific business needs or document types. This feature is particularly beneficial for recognizing text in specialized documents or uncommon fonts.

Emgu CV

Invoice OCR Open Source (Free & Paid Tools Comparison): Figure 1 - Emgu CV webpage

Emgu CV C# is a .NET wrapper of the OpenCV library. It helps developers easily use OpenCV's functionality within their C# projects. It provides a rich toolkit for image processing, computer vision, and other domains related to it. It can be very useful for processing invoices to extract structured data.

It utilizes the Tesseract OCR engine to extract text from images and documents. This step demands accuracy as it is the main step of data extraction from any invoice. The main method of this wrapper is Tesseract.Recognize() as it converts the text from image to editable and searchable data. Developers can enhance the efficiency of workflows of invoice processing.

Advantages of Emgu CV

Cross-Platform: Emgu CV is functional on any platform that supports .NET, including iOS, Android, Mac OS, Linux, and Windows.

Cross-Language: Beyond C#, Emgu CV is accessible in several languages, including VB.NET, C++, and IronPython. It provides extensive example code and robust support through its documentation.

At9T

Invoice OCR Open Source (Free & Paid Tools Comparison): Figure 2 - At9T webpage

At9T, also known as (a9t9), offers a free OCR (Optical Character Recognition) software application. This software can be used to extract data from PDFs and images using a beautiful graphical user interface (GUI). It is completely written in C# language. It provides a very simple and easy-to-use way to convert PDFs into searchable documents using its intelligent document processing.

Its GUI helps to extend its market to non-developer people who want solutions at one click. This software is very easy to install and use. It can be used for personal and professional use. It can perform many OCR tasks efficiently. We can upload PDF invoices and extract the invoice data like invoice date, line items, totals, etc. You need to upload and press a button to start OCR, and it'll start processing invoices.

Features of At9T

User-Friendly Interface: Its user interface is straightforward to use. It was designed with simplicity in mind. Any person with no experience can use it easily.

Multiple Language Support: It supports multiple languages like English, Dutch, Japanese, Korean, and many more.

Batch Processing: This software can do OCR of multiple files at the same time. It'll save time if you want to extract data from a large number of files.

Introducing IronOCR: An Advanced OCR Solution

Invoice OCR Open Source (Free & Paid Tools Comparison): Figure 3 - IronOCR webpage

As we discussed above, open-source options have many difficulties. Like Tesseract is not easy to integrate into our projects; it needs a wrapper to use it. To use Emgu CV, you must know OpenCV. Otherwise, it'll be a steep learning experience for you, and it also does not have extensive documentation. At the same time, At9T is not suitable for complex documents.

To overcome these issues and advance OCR solutions, IronOCR is the best option. IronOCR is a .NET OCR library that extends the capabilities of Tesseract 5 Engine and adds more advanced options for OCR. Unlike Tesseract and other libraries, it is very easy to integrate in .NET projects.

IronOCR supports multiple document formats, including PDFs, PNG, JPG, BMP, and others. It supports a wide range of .NET frameworks and platforms, including Windows, macOS, and others. You can perform OCR actions in over 127 languages, which makes it a global OCR product. You can extract data from all invoice formats using its amazing invoice OCR technology. IronOCR uses machine learning for best text recognition. Let's have a look at the key features of IronOCR.

Key Features of IronOCR

Here's an organized summary of its key features:

Input Flexibility: Reads from a variety of formats, including images (JPG, PNG, BMP), multi-page/frame files (TIFF, GIF), and System.Drawing objects, streams, and PDFs with optimized DPI.

Advanced Filters: A range of filters like the Filter Wizard, Image Correction (sharpening, resolution enhancement, denoise, dilate, erode), Image Orientation Correction (rotate, deskew, scale), and Color Correction (binarize, grayscale, invert, replace color, select text color) are available to ensure optimal image quality before OCR.

Region Selection: Allows specific regions of the document to be selected for OCR through CropRectangle.

Data Output: Provides simple data output as .NET text strings, barcodes, QR data, and images.

Structured Data: Offers structured data output in the form of pages, blocks, paragraphs, lines, words, and characters.

Document Export: Enables export of documents as searchable PDFs, HTML, or as images of pages, text, barcode, or QR.

Text Highlighting & Saving: Functionality to highlight and save characters, words, lines, and paragraphs.

Languages & Frameworks: Supports C#, VB.NET, F#, and compatible with .NET 8, 7, 6, 5, Core 2x & 3x, Standard 2, and Framework 4.6.2+.

Operating Systems: Versatile compatibility with Microsoft Windows, macOS, Linux, Docker, Azure, and AWS.

IDE Support: Fully supported on Microsoft Visual Studio and JetBrains ReSharper & Rider.

Example

Here is the example code to extract data from the invoice using IronOCR:

// Create IronOCR Tesseract Instance
IronTesseract tesseract = new IronTesseract();
// Create an OcrInput object
using (OcrInput input = new OcrInput("sample_invoice.png")) // You can directly pass the image path to the constructor
{
    // Read and store OcrResults object
    OcrResult result = tesseract.Read(input);
    // Get all text from the OCR result
    string allText = result.Text;
    // Print to console
    Console.WriteLine(allText);
}

// Create IronOCR Tesseract Instance
IronTesseract tesseract = new IronTesseract();
// Create an OcrInput object
using (OcrInput input = new OcrInput("sample_invoice.png")) // You can directly pass the image path to the constructor
{
    // Read and store OcrResults object
    OcrResult result = tesseract.Read(input);
    // Get all text from the OCR result
    string allText = result.Text;
    // Print to console
    Console.WriteLine(allText);
}

' Create IronOCR Tesseract Instance
Dim tesseract As New IronTesseract()
' Create an OcrInput object
Using input As New OcrInput("sample_invoice.png") ' You can directly pass the image path to the constructor
	' Read and store OcrResults object
	Dim result As OcrResult = tesseract.Read(input)
	' Get all text from the OCR result
	Dim allText As String = result.Text
	' Print to console
	Console.WriteLine(allText)
End Using

VB C#

Here is the output data which we extracted from the invoice image:

Invoice OCR Open Source (Free & Paid Tools Comparison): Figure 4 - Output using the previous code to extract text from a sample invoice

We can do data analysis using data recognition and export it into a CSV file.

Conclusion

In conclusion, when we talk about reading text from images or documents (OCR technology), we have many choices. Tesseract OCR, Emgu CV, and At9T are all free tools that people can use. Each one is good in its own way.

But if you need something more advanced in invoice OCR, and if it suits your needs, you can begin a license starting at $599.

So, whether you're a programmer looking to add text-reading features to your project or a business wanting to handle your documents better, there are many options. Free tools like Tesseract, Emgu CV, and At9T are good starting points. But for something more professional, IronOCR offers a lot of advanced features. The key is to choose the right tool for your specific needs.