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(@"example.tiff")) { 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 March 29, 2023

OCR With Computer Vision (Example Tutorial)

In today's digital age, data is a valuable asset, and the demand for data processing and automation is increasing rapidly. Organizations often rely on scanned images, documents, and other sources to extract meaningful information, but it can be a time-consuming and error-prone process when done manually.

Optical Character Recognition (OCR) is a technology that enables machines to read and interpret the text from images, making data processing and automation faster and more efficient. In this article, we will explore OCR computer vision using IronOCR and how it can enhance text recognition.

Why OCR is important?

OCR along with computer vision is an advanced form of Optical Character Recognition (OCR) that leverages the power of artificial intelligence and machine learning algorithms to recognize text characters from images more accurately and efficiently.

Computer vision image processing algorithms allow OCR systems to understand the context and layout of text in an image and recognize characters based on their shape and structure. OCR along with computer vision can extract text from complex images with multiple fonts, styles, and sizes, making it a valuable tool in document digitization, data extraction, and automation.

IronOCR: C# OCR Library

IronOCR is a popular OCR library that uses computer vision techniques for text extraction from images and documents. It is easy to use and integrates with multiple programming languages, including C# and VB.NET. IronOCR is available in both on-premise and cloud versions and offers a range of functionalities to process and extract text from images.

Installing IronOCR

To install IronOCR, use the following command in the NuGet Package Manager Console:

Install-Package IronOcr.ComputerVision.Windows

OCR System with IronOCR

I'll use the following image to test the OCR System with Computer Vision using IronOCR.

FindTextRegion

The FindTextRegion method is used to identify a single text region within an image. The method takes several optional parameters, including Scale, DilationAmount, Binarize, and Invert. Scale adjusts the size of the image, DilationAmount increases the thickness of the text, Binarize converts the image into black and white, and Invert inverts the colors of the image.

using IronOcr;
using System;
var ocr = new IronTesseract();
using (var inputOCR = new OcrInput("test.jpg")) 
{
    inputOCR.FindTextRegion();
    OcrResult result = ocr.Read(input);
    string resultText = result.Text;
    Console.WriteLine(resultText);
}

using IronOcr;
using System;
var ocr = new IronTesseract();
using (var inputOCR = new OcrInput("test.jpg")) 
{
    inputOCR.FindTextRegion();
    OcrResult result = ocr.Read(input);
    string resultText = result.Text;
    Console.WriteLine(resultText);
}

Imports IronOcr
Imports System
Private ocr = New IronTesseract()
Using inputOCR = New OcrInput("test.jpg")
	inputOCR.FindTextRegion()
	Dim result As OcrResult = ocr.Read(input)
	Dim resultText As String = result.Text
	Console.WriteLine(resultText)
End Using

VB C#

After running the code, you'll see that the code is finding the text region using machine learning. The above code will find the text region and extract the text through text recognition using a machine learning process. You'll see the output result comes up in the console with almost 100% text recognition accuracy. IronOCR's accuracy is almost 100% in every form of text even if it is printed or handwritten text.

FindMultipleTextRegions Method

The FindMultipleTextRegions method is similar to the FindTextRegion method, but it is used when there are multiple text regions in an image. It returns a list of CropRectangle objects that define the location of each text region. This method is useful when you want to extract text from an image that contains multiple sections of text.

using IronOcr;
var ocr = new IronTesseract();
using (var input = new OcrInput("test.jpg"))
{
    input.FindMultipleTextRegions(Scale: 2.0, DilationAmount: -1, Binarize: true, Invert: false);
    OcrResult result = ocr.Read(input);
    string resultText = result.Text;
    Console.WriteLine(resultText);
}

using IronOcr;
var ocr = new IronTesseract();
using (var input = new OcrInput("test.jpg"))
{
    input.FindMultipleTextRegions(Scale: 2.0, DilationAmount: -1, Binarize: true, Invert: false);
    OcrResult result = ocr.Read(input);
    string resultText = result.Text;
    Console.WriteLine(resultText);
}

Imports IronOcr
Private ocr = New IronTesseract()
Using input = New OcrInput("test.jpg")
	input.FindMultipleTextRegions(Scale:= 2.0, DilationAmount:= -1, Binarize:= True, Invert:= False)
	Dim result As OcrResult = ocr.Read(input)
	Dim resultText As String = result.Text
	Console.WriteLine(resultText)
End Using

VB C#

The code snippet provided above is an example of how to use the IronOCR library to perform OCR on an image file. It first imports the IronOCR library and creates a new instance of the IronTesseract class. Then, it initializes an OcrInput object with the path of the input image file and applies some pre-processing techniques using the FindMultipleTextRegions method.

After that, it calls the Read method of the IronTesseract object, which performs the OCR on the pre-processed image and returns an OcrResult object. The text extracted from the OcrResult object is then stored in a string variable and printed to the console.

The output of IronOCR

The output of IronOCR is very accurate, even when dealing with complex images with multiple fonts, sizes, and styles of text.

OCR Accuracy is important when extracting data from images because the extracted text is often used for further processing, such as data analysis, manual data entry machine learning, or natural language processing. If the extracted text contains errors, it can cause problems downstream.

Use Cases of OCR Computer Vision

Optical Character Recognition (OCR) technology has revolutionized the way we handle printed and handwritten text. OCR tools have become an indispensable part of document processing and data extraction. Here are some use cases of Optical Character Recognition software:

OCR License Plate Recognition

License plate recognition plays a significant role in automating traffic management, parking systems, and law enforcement activities. By implementing OCR computer vision in C#, developers can create applications that quickly and accurately identify license plates from images or live video feeds. This technology can be used to:

Monitor traffic violations and identify vehicles involved in criminal activities.
Automate the parking systems, facilitating entry and exit management and streamlining the billing process.
Enhance security measures by tracking and monitoring vehicle movement in restricted areas.

Extracting Text from Invoices

OCR computer vision in C# can be utilized to develop OCR applications that automate the extraction of text from invoices and other financial documents. This process can drastically reduce manual data entry errors and streamline accounting tasks. Key benefits include:

Increased productivity by automating the data entry process.
Improved accuracy, as OCR reduces the likelihood of human errors.
Seamless integration with accounting software and systems for efficient data management.

OCR Subtitles Generation

Creating subtitles for videos can be time-consuming and labor-intensive. OCR computer vision in C# can simplify this process by automatically detecting and transcribing the on-screen text, enabling developers to:

Create accurate subtitles for movies, TV shows, and online videos.
Enhance accessibility for individuals with hearing impairments or those who speak different languages.
Boost SEO efforts by providing searchable, indexable content for video platform

OCR PDF Processing

PDFs are widely used for sharing and storing documents, but extracting text from them can be challenging. OCR computer vision in C# can help developers build OCR applications that effortlessly process PDF files and extract their content, facilitating:

Easy conversion of PDFs into editable file formats like Word, Excel, or plain text.
Efficient data extraction for analysis, indexing, or further processing.
Improved accessibility by converting scanned PDFs into searchable, readable text.

Digitizing Printed Text

OCR software is widely used to digitize printed text from document images. OCR tools can extract text from scanned digital documents, PDFs, and images in various formats. This is particularly useful in document management, where you can easily search, store, and share text-based documents.

Extracting Handwritten Text

OCR technology has advanced to a point where it can recognize handwritten text with high accuracy. This is particularly useful in fields such as healthcare, where medical records often contain handwritten notes. OCR tools can extract handwritten text from medical records, prescription labels, and other handwritten documents.

Data Extraction

OCR technology is widely used to extract data from input data such as invoices, receipts, and forms. OCR models can recognize and extract key data fields such as names, addresses, dates, and amounts. This eliminates the need for manual data entry and reduces errors in the data processing.

Image search

OCR technology is also used for image search, where you can search for images based on the text contained within them. This is particularly useful for large image libraries, where manual searching would be time-consuming.

Translation

OCR software can be used to extract text from documents in one language and translate it into another language. This is particularly useful for international businesses, where documents need to be translated quickly and accurately.

Summary

Optical character recognition (OCR) is a technology that enables computers to read text from images. OCR along with computer vision is important because it allows machines to understand and interpret the visual world, which is essential for applications such as self-driving cars, robotics, and automated document processing.

IronOCR is a powerful OCR engine that can be used to apply OCR with computer vision to accurately recognize text and perform text extraction from images. It provides a range of methods for finding and extracting text regions, including FindTextRegion, FindMultipleTextRegions, and GetTextRegions. Each method has its own set of parameters that can be used to fine-tune the OCR process and provides high OCR accuracy.

By using IronOCR, you can extract the scanned text from input images quickly and accurately, which can save you time and effort when dealing with large volumes of input image data. Whether you are working with scanned documents, photographs, or screenshots, IronOCR can help you unlock the text contained within.

IronOCR offers a 30-day free trial to users who want to test the software before making a purchase decision. The license for IronOCR starts from $499 and includes support and updates for one year. With its robust features and reasonable pricing, IronOCR is a great option for anyone looking for a reliable OCR solution with high OCR accuracy.

Examples