IronOCR How-Tos .NET MAUI OCR How to use Computer Vision to Find Text ByChaknith Bin September 26, 2022 Updated June 22, 2025 Share: IronOCR utilizes OpenCV to use Computer Vision to detect areas where text exists in an image. This is useful for images that contain a lot of noise, images with text in many different places, and images where text is warped. The use of computer vision in IronOCR will determine where text regions exist and then use Tesseract to attempt to read those regions.How to OCR License Plate in C# (Tutorial)How to Get Text From Invoice in C# TutorialHow to OCR Get Text From Screenshot in C#How to OCR Subtitles in C# (Tutorial) View the IronOCR YouTube Playlist Steps to Use OCR With Computer Vision Download C# library to use OCR with Computer Vision Utilize FindTextRegion method to auto detect text regions Check which text region got detected with StampCropRectangleAndSaveAs method Use computer vision to separate the original image into images based on text regions with FindMultipleTextRegions method Use GetTextRegions method to get crop areas list where text was detected IronOCR.ComputerVision Installation via NuGet Package OpenCV methods that perform Computer Vision in IronOCR are visible in the regular IronOCR NuGet package. Use of these methods requires NuGet installation of IronOcr.ComputerVision to the solution. You are prompted to download it if you do not have it installed. Windows: IronOcr.ComputerVision.Windows Linux: IronOcr.ComputerVision.Linux macOS: IronOcr.ComputerVision.MacOS macOS ARM: IronOcr.ComputerVision.MacOS.ARM Install using the NuGet Package Manager or paste the following in the Package Manager Console: Install-Package IronOcr.ComputerVision.Windows This will provide the necessary assemblies to use IronOCR Computer Vision with our model file. Functionality and API Code Examples are included further down this tutorial. Here is a general overview of the methods that are currently available: Method Explanation FindTextRegion Detect regions which contain text elements and instruct Tesseract to only search for text within the area in which text was detected. FindMultipleTextRegions Detect areas which contain text elements and divide the page into separate images based on text regions. GetTextRegions Scans the image and returns a list of text regions as `List`. FindTextRegion Usage of FindTextRegion will use computer vision to detect regions which contain text elements on every page of an OcrInput object. :path=/static-assets/ocr/content-code-examples/how-to/computer-vision-findtextregion-1.cs using IronOcr; // Initialize an instance of IronTesseract for OCR processing var ocr = new IronTesseract(); // Create an OcrInput instance to hold the image being processed using var input = new OcrInput(); // Load an image from the specified file path to be processed // Ensure this file path is correct and accessible input.AddImage("/path/to/file.png"); // Perform OCR on the input image to extract text region and process it OcrResult result = ocr.Read(input); // Retrieve and store the extracted text from the OCR result string resultText = result.Text; // Add additional operations as needed to work with the extracted text // For example: // Console.WriteLine(resultText); Imports IronOcr ' Initialize an instance of IronTesseract for OCR processing Private ocr = New IronTesseract() ' Create an OcrInput instance to hold the image being processed Private input = New OcrInput() ' Load an image from the specified file path to be processed ' Ensure this file path is correct and accessible input.AddImage("/path/to/file.png") ' Perform OCR on the input image to extract text region and process it Dim result As OcrResult = ocr.Read(input) ' Retrieve and store the extracted text from the OCR result Dim resultText As String = result.Text ' Add additional operations as needed to work with the extracted text ' For example: ' Console.WriteLine(resultText); $vbLabelText $csharpLabel Can optionally be called with custom parameters: :path=/static-assets/ocr/content-code-examples/how-to/computer-vision-findtextregion-2.cs using IronOcr; // Initialize the IronTesseract OCR engine var ocr = new IronTesseract(); // Create an OCR input object to hold the image(s) for processing using var input = new OcrInput(); // Load the image from a specified file path // Note: Ensure that the file path is correct and accessible input.AddImage("/path/file.png"); // Enhance the OCR process by adjusting the image properties // Scale: Magnifies the image to better detect characters // DilationAmount: Increases the thickness of characters to improve recognition // Binarize: Converts the image to black and white, enhancing contrast // Invert: Reverses the colors, sometimes necessary for certain images // Note: These enhancements can significantly affect the OCR results input.AddAdvancedImagePreprocessing(filter => { filter.Invert(); // Reverse the colors filter.Binarize(); // Enhance contrast by converting to black and white filter.Dilate(20); // Increase thickness of characters for better recognition filter.Resize(Scale: 2.0); // Magnify image to better detect characters }); // Perform OCR on the input and obtain the result OcrResult result = ocr.Read(input); // Extract the recognized text from the OCR result // Note: 'result.Text' contains the text extracted from the image, if any. string resultText = result.Text; Imports IronOcr ' Initialize the IronTesseract OCR engine Private ocr = New IronTesseract() ' Create an OCR input object to hold the image(s) for processing Private input = New OcrInput() ' Load the image from a specified file path ' Note: Ensure that the file path is correct and accessible input.AddImage("/path/file.png") ' Enhance the OCR process by adjusting the image properties ' Scale: Magnifies the image to better detect characters ' DilationAmount: Increases the thickness of characters to improve recognition ' Binarize: Converts the image to black and white, enhancing contrast ' Invert: Reverses the colors, sometimes necessary for certain images ' Note: These enhancements can significantly affect the OCR results input.AddAdvancedImagePreprocessing(Sub(filter) filter.Invert() filter.Binarize() filter.Dilate(20) filter.Resize(Scale:= 2.0) End Sub) ' Perform OCR on the input and obtain the result Dim result As OcrResult = ocr.Read(input) ' Extract the recognized text from the OCR result ' Note: 'result.Text' contains the text extracted from the image, if any. Dim resultText As String = result.Text $vbLabelText $csharpLabel In this example, I will use the following image for a method I am writing which needs to crop to areas containing text but input images may vary in text location. In this case, I can use FindTextRegion to narrow down the scan to an area that Computer Vision has detected text. This is an example image: :path=/static-assets/ocr/content-code-examples/how-to/computer-vision-findtextregion-3.cs using IronOcr; using IronSoftware.Drawing; // Import IronSoftware.Drawing for handling drawing related functionalities using System; using System.Linq; // Import LINQ for handling collections // Create an instance of IronTesseract, which is responsible for OCR operations var ocr = new IronTesseract(); // Use an 'using' statement to automatically dispose of resources when done using var input = new OcrInput(); // Load the image file to perform OCR input.AddImage("wh-words-sign.jpg"); // Find the text region using computer vision techniques // This step is crucial for narrowing down the area of interest in the image var pages = ocr.Read(input); // Perform OCR to get the pages first var textCropArea = pages.Pages.First().FindTextRegion(); // Debugging: Stamp the identified text region onto the image with a red rectangle // and save it as a new file. This helps visually verify the identified text area. input.DrawRectangle(textCropArea, System.Drawing.Color.Red); // Correct method to draw the rectangle in IronSoftware input.SaveAs("image_text_area.png", AnyBitmap.ImageFormat.Png); // Save the drawn image // Once the text region looks good from the generated image, perform OCR on the specific region var ocrResult = ocr.Read("wh-words-sign.jpg", textCropArea); // Output the recognized text to the console Console.WriteLine(ocrResult.Text); Imports IronOcr Imports IronSoftware.Drawing ' Import IronSoftware.Drawing for handling drawing related functionalities Imports System Imports System.Linq ' Import LINQ for handling collections ' Create an instance of IronTesseract, which is responsible for OCR operations Private ocr = New IronTesseract() ' Use an 'using' statement to automatically dispose of resources when done Private input = New OcrInput() ' Load the image file to perform OCR input.AddImage("wh-words-sign.jpg") ' Find the text region using computer vision techniques ' This step is crucial for narrowing down the area of interest in the image Dim pages = ocr.Read(input) ' Perform OCR to get the pages first Dim textCropArea = pages.Pages.First().FindTextRegion() ' Debugging: Stamp the identified text region onto the image with a red rectangle ' and save it as a new file. This helps visually verify the identified text area. input.DrawRectangle(textCropArea, System.Drawing.Color.Red) ' Correct method to draw the rectangle in IronSoftware input.SaveAs("image_text_area.png", AnyBitmap.ImageFormat.Png) ' Save the drawn image ' Once the text region looks good from the generated image, perform OCR on the specific region Dim ocrResult = ocr.Read("wh-words-sign.jpg", textCropArea) ' Output the recognized text to the console Console.WriteLine(ocrResult.Text) $vbLabelText $csharpLabel Now this code has two outputs, the first is a .png file saved by StampCropRectangleAndSaveAs which is used for debugging. We can see where IronCV (Computer Vision) thought the text was: Looks pretty good. Now the second output is the Text itself which is: IRONSOFTWARE 50,000+ Developers in our active community 10,777,061 19,313 NuGet downloads Support tickets resolved 50%+ 80%+ Engineering Team growth Support Team growth $25,000+ Raised with #TEAMSEAS to clean our beaches & waterways FindMultipleTextRegions Usage of FindMultipleTextRegions takes all pages of an OcrInput object and uses computer vision to detect areas which contain text elements and divide the input into separate images based on text regions: :path=/static-assets/ocr/content-code-examples/how-to/computer-vision-findmultipletextregions-1.cs using IronOcr; // Create a new instance of the OCR engine var ocr = new IronTesseract(); // Initialize a new OCR input using var input = new OcrInput(); // Load an image file into the OCR input // Make sure the file path is correct and the file exists input.AddImage("/path/file.png"); // Perform OCR on the loaded image and get the result OcrResult result = ocr.Read(input); // Extract the recognized text from the OCR result string resultText = result.Text; // The `resultText` variable now contains all text extracted from the image // You can easily use this result in further processing or display it Imports IronOcr ' Create a new instance of the OCR engine Private ocr = New IronTesseract() ' Initialize a new OCR input Private input = New OcrInput() ' Load an image file into the OCR input ' Make sure the file path is correct and the file exists input.AddImage("/path/file.png") ' Perform OCR on the loaded image and get the result Dim result As OcrResult = ocr.Read(input) ' Extract the recognized text from the OCR result Dim resultText As String = result.Text ' The `resultText` variable now contains all text extracted from the image ' You can easily use this result in further processing or display it $vbLabelText $csharpLabel Can optionally be called with custom parameters: :path=/static-assets/ocr/content-code-examples/how-to/computer-vision-findmultipletextregions-2.cs using IronOcr; // Create an instance of IronTesseract, which is the main class for performing OCR. var ocr = new IronTesseract(); // Use a 'using' statement to ensure the OcrInput resources are disposed of after use. using var input = new OcrInput(); // Load an image from the specified path into the OCR input object. input.AddImage("/path/file.png"); // Use AddImage according to IronOcr's latest convention. /* * FindMultipleTextRegions method attempts to enhance OCR by attempting * to find and resolve multiple regions of text within an image. * Parameters: * scale - (double) Adjusts the scale of the image to detect smaller text. Default is 1.0. * dilationAmount - (int) Specifies the extent of dilation for creating a mask. * Negative values might be invalid, so a non-negative value (e.g., 1) is often used. * binarize - (bool) If true, the image will be converted to two colors: black and white. * invert - (bool) If true, inverts the colors of the image. */ try { input.FindMultipleTextRegions(scale: 2.0, dilationAmount: 1, binarize: true, invert: false); // Use the Read method to perform OCR on the specified input, retrieving the result object. OcrResult result = ocr.Read(input); // Get the recognized text from the OCR result object. string resultText = result.Text; // Output the recognized text to the console. Console.WriteLine(resultText); } catch (Exception ex) { // Catch potential exceptions and output the message to the console. Console.WriteLine("An error occurred during OCR processing: " + ex.Message); } Imports IronOcr ' Create an instance of IronTesseract, which is the main class for performing OCR. Private ocr = New IronTesseract() ' Use a 'using' statement to ensure the OcrInput resources are disposed of after use. Private input = New OcrInput() ' Load an image from the specified path into the OCR input object. input.AddImage("/path/file.png") ' Use AddImage according to IronOcr's latest convention. ' ' * FindMultipleTextRegions method attempts to enhance OCR by attempting ' * to find and resolve multiple regions of text within an image. ' * Parameters: ' * scale - (double) Adjusts the scale of the image to detect smaller text. Default is 1.0. ' * dilationAmount - (int) Specifies the extent of dilation for creating a mask. ' * Negative values might be invalid, so a non-negative value (e.g., 1) is often used. ' * binarize - (bool) If true, the image will be converted to two colors: black and white. ' * invert - (bool) If true, inverts the colors of the image. ' Try input.FindMultipleTextRegions(scale:= 2.0, dilationAmount:= 1, binarize:= True, invert:= False) ' Use the Read method to perform OCR on the specified input, retrieving the result object. Dim result As OcrResult = ocr.Read(input) ' Get the recognized text from the OCR result object. Dim resultText As String = result.Text ' Output the recognized text to the console. Console.WriteLine(resultText) Catch ex As Exception ' Catch potential exceptions and output the message to the console. Console.WriteLine("An error occurred during OCR processing: " & ex.Message) End Try $vbLabelText $csharpLabel Another overload method of FindMultipleTextRegions takes an OCR Page and returns a list of OCR Pages, one for each Text region on it: :path=/static-assets/ocr/content-code-examples/how-to/computer-vision-findmultipletextregions-3.cs using IronOcr; using System.Collections.Generic; using System.Linq; // Initialize the page index to select a specific page int pageIndex = 0; // Create a new instance of OcrInput to handle OCR operations using var input = new OcrInput(); // Load an image from the given path into the OCR input for processing input.AddImage("/path/file.png"); // Retrieve the selected page based on the pageIndex var selectedPage = input.Pages[pageIndex]; // Find and list multiple text regions on the selected page List<OcrResult.TextRegion> textRegionsOnPage = selectedPage.FindTextRegions().ToList(); // Note: The type OcrInput.OcrInputPage does not appear to be valid, replaced with an inferred correct type OcrResult.TextRegion. // The original GetPages() method assumption was addressed correctly by utilizing the Pages collection property. Imports IronOcr Imports System.Collections.Generic Imports System.Linq ' Initialize the page index to select a specific page Private pageIndex As Integer = 0 ' Create a new instance of OcrInput to handle OCR operations Private input = New OcrInput() ' Load an image from the given path into the OCR input for processing input.AddImage("/path/file.png") ' Retrieve the selected page based on the pageIndex Dim selectedPage = input.Pages(pageIndex) ' Find and list multiple text regions on the selected page Dim textRegionsOnPage As List(Of OcrResult.TextRegion) = selectedPage.FindTextRegions().ToList() ' Note: The type OcrInput.OcrInputPage does not appear to be valid, replaced with an inferred correct type OcrResult.TextRegion. ' The original GetPages() method assumption was addressed correctly by utilizing the Pages collection property. $vbLabelText $csharpLabel GetTextRegions Usage of GetTextRegions returns a list of crop areas where text was detected in a page: :path=/static-assets/ocr/content-code-examples/how-to/computer-vision-gettextregions.cs using IronOcr; using IronSoftware.Drawing; using System.Linq; // Example code to demonstrate how to load an image and work with OCR (Optical Character Recognition) for a specific page. int pageIndex = 0; // Create an instance of OcrInput to load image files for OCR processing. using var input = new OcrInput(); // Load an image from the specified file path into the OCR input. // Make sure that the file path is correct and that the file exists. input.AddImage("/path/file.png"); // Retrieve a specific page from the loaded OCR input. // Ensure that the pageIndex is within the range of available pages. var selectedPage = input.ToList()[pageIndex]; // The following line is commented out, but it can be used to get text regions from the selected page. // Uncomment and use if needed to get regions of recognized text from the page. // List<Rectangle> regions = selectedPage.GetTextRegions(); Imports IronOcr Imports IronSoftware.Drawing Imports System.Linq ' Example code to demonstrate how to load an image and work with OCR (Optical Character Recognition) for a specific page. Private pageIndex As Integer = 0 ' Create an instance of OcrInput to load image files for OCR processing. Private input = New OcrInput() ' Load an image from the specified file path into the OCR input. ' Make sure that the file path is correct and that the file exists. input.AddImage("/path/file.png") ' Retrieve a specific page from the loaded OCR input. ' Ensure that the pageIndex is within the range of available pages. Dim selectedPage = input.ToList()(pageIndex) ' The following line is commented out, but it can be used to get text regions from the selected page. ' Uncomment and use if needed to get regions of recognized text from the page. ' List<Rectangle> regions = selectedPage.GetTextRegions(); $vbLabelText $csharpLabel Specific Use Case Guides With the right settings and input files, OCR can be a very powerful tool. It can almost perfectly imitate the reading capability of a human. Frequently Asked Questions What is the purpose of using Computer Vision to find text? IronOCR uses Computer Vision to detect areas where text exists in an image, which helps in processing images with noise, text in different places, or warped text. How can I install the necessary components for Computer Vision via NuGet? You can install IronOCR.ComputerVision via NuGet by using the Package Manager Console with the command: Install-Package IronOcr.ComputerVision.Windows. There are also packages available for Linux and macOS. What does the FindTextRegion method do? The FindTextRegion method in IronOCR detects regions in an image that contain text elements and instructs Tesseract to only search for text within those areas. Can I use custom parameters with text region detection methods? Yes, you can provide custom parameters to the FindTextRegion method in IronOCR to refine detection, such as setting the minimum text height and allowing subregions. What is the purpose of detecting multiple text regions in an image? The FindMultipleTextRegions method in IronOCR is used to detect areas with text and divide the input into separate images based on these text regions. How can I retrieve areas where text was detected? You can use the GetTextRegions method in IronOCR on an OcrInput object to get a list of CropRectangle areas where text was detected. What are the installation packages available for Computer Vision? Installation packages for IronOCR.ComputerVision are available for Windows, Linux, macOS, and macOS ARM. How are images with multiple text regions processed? IronOCR can handle images with multiple text regions using the FindMultipleTextRegions method, which divides the input into separate images based on detected text regions. Are there code examples available for using Computer Vision in image processing? Yes, the tutorial provides code examples demonstrating how to use methods like FindTextRegion and FindMultipleTextRegions with IronOCR. What is required to use Computer Vision capabilities in image processing? To use IronOCR's Computer Vision capabilities, you need to install the IronOcr.ComputerVision package through NuGet and reference the necessary namespaces in your C# project. Chaknith Bin Chat with engineering team now Software Engineer Chaknith works on IronXL and IronBarcode. He has deep expertise in C# and .NET, helping improve the software and support customers. His insights from user interactions contribute to better products, documentation, and overall experience. Ready to Get Started? Free NuGet Download Total downloads: 3,904,374 View Licenses