1. IronOCR
  2. How-Tos
  3. .NET MAUI OCR

How to use Computer Vision to Find Text

Introduction

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. Use of computer vision in IronOCR will determine where text regions exists and then use Tesseract to attempt to read those regions.

Steps to Use OCR With Computer Vision

  1. Download C# library to use OCR with Computer Vision
  2. Utilize FindTextRegion method to auto detect text regions
  3. Check which text region get detected with StampCropRectangleAndSaveAs method
  4. Use computer vision to separate original image into images based on text regions with FindMultipleTextRegions method
  5. 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 install of IronOcr.ComputerVision to the solution, you are prompted to download 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:

PM> 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:

MethodExplanation
FindTextRegionDetect regions which contain text elements and instruct Tesseract to only search for text within the area in which text was detected.
FindMultipleTextRegionsDetect areas which contain text elements and divide the page into separate images based on text regions.
GetTextRegionsScans 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;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("/path/file.png");

input.FindTextRegion();
OcrResult result = ocr.Read(input);
string resultText = result.Text;
Imports IronOcr

Private ocr = New IronTesseract()
Private input = New OcrInput()
input.LoadImage("/path/file.png")

input.FindTextRegion()
Dim result As OcrResult = ocr.Read(input)
Dim resultText As String = result.Text
VB   C#

Can optionally be called with custom parameters:

:path=/static-assets/ocr/content-code-examples/how-to/computer-vision-findtextregion-2.cs
using IronOcr;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("/path/file.png");

input.FindTextRegion(Scale: 2.0, DilationAmount: 20, Binarize: true, Invert: true);
OcrResult result = ocr.Read(input);
string resultText = result.Text;
Imports IronOcr

Private ocr = New IronTesseract()
Private input = New OcrInput()
input.LoadImage("/path/file.png")

input.FindTextRegion(Scale:= 2.0, DilationAmount:= 20, Binarize:= True, Invert:= True)
Dim result As OcrResult = ocr.Read(input)
Dim resultText As String = result.Text
VB   C#

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:

Image with Text
:path=/static-assets/ocr/content-code-examples/how-to/computer-vision-findtextregion-3.cs
using IronOcr;
using IronSoftware.Drawing;
using System;
using System.Linq;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("wh-words-sign.jpg");

// Find the text region using Computer Vision
Rectangle textCropArea = input.GetPages().First().FindTextRegion();

// For debugging and demonstration purposes, lets see what region it found:
input.StampCropRectangleAndSaveAs(textCropArea, Color.Red, "image_text_area", AnyBitmap.ImageFormat.Png);

// Looks good, so let us apply this region to hasten the read:
var ocrResult = ocr.Read("wh-words-sign.jpg", textCropArea);
Console.WriteLine(ocrResult.Text);
Imports IronOcr
Imports IronSoftware.Drawing
Imports System
Imports System.Linq

Private ocr = New IronTesseract()
Private input = New OcrInput()
input.LoadImage("wh-words-sign.jpg")

' Find the text region using Computer Vision
Dim textCropArea As Rectangle = input.GetPages().First().FindTextRegion()

' For debugging and demonstration purposes, lets see what region it found:
input.StampCropRectangleAndSaveAs(textCropArea, Color.Red, "image_text_area", AnyBitmap.ImageFormat.Png)

' Looks good, so let us apply this region to hasten the read:
Dim ocrResult = ocr.Read("wh-words-sign.jpg", textCropArea)
Console.WriteLine(ocrResult.Text)
VB   C#

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:

Image with Text Area Highlighted

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;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("/path/file.png");

input.FindMultipleTextRegions();
OcrResult result = ocr.Read(input);
string resultText = result.Text;
Imports IronOcr

Private ocr = New IronTesseract()
Private input = New OcrInput()
input.LoadImage("/path/file.png")

input.FindMultipleTextRegions()
Dim result As OcrResult = ocr.Read(input)
Dim resultText As String = result.Text
VB   C#

Can optionally be called with custom parameters:

:path=/static-assets/ocr/content-code-examples/how-to/computer-vision-findmultipletextregions-2.cs
using IronOcr;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("/path/file.png");

input.FindMultipleTextRegions(Scale: 2.0, DilationAmount: -1, Binarize: true, Invert: false);
OcrResult result = ocr.Read(input);
string resultText = result.Text;
Imports IronOcr

Private ocr = New IronTesseract()
Private input = New OcrInput()
input.LoadImage("/path/file.png")

input.FindMultipleTextRegions(Scale:= 2.0, DilationAmount:= -1, Binarize:= True, Invert:= False)
Dim result As OcrResult = ocr.Read(input)
Dim resultText As String = result.Text
VB   C#

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;

int pageIndex = 0;
using var input = new OcrInput();
input.LoadImage("/path/file.png");

var selectedPage = input.GetPages().ElementAt(pageIndex);
List<OcrInputPage> textRegionsOnPage = selectedPage.FindMultipleTextRegions();
Imports IronOcr
Imports System.Collections.Generic
Imports System.Linq

Private pageIndex As Integer = 0
Private input = New OcrInput()
input.LoadImage("/path/file.png")

Dim selectedPage = input.GetPages().ElementAt(pageIndex)
Dim textRegionsOnPage As List(Of OcrInputPage) = selectedPage.FindMultipleTextRegions()
VB   C#

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.Collections.Generic;
using System.Linq;

int pageIndex = 0;
using var input = new OcrInput();
input.LoadImage("/path/file.png");

var selectedPage = input.GetPages().ElementAt(pageIndex);
// List<Rectangle> regions = selectedPage.GetTextRegions();
Imports IronOcr
Imports IronSoftware.Drawing
Imports System.Collections.Generic
Imports System.Linq

Private pageIndex As Integer = 0
Private input = New OcrInput()
input.LoadImage("/path/file.png")

Dim selectedPage = input.GetPages().ElementAt(pageIndex)
' List<Rectangle> regions = selectedPage.GetTextRegions();
VB   C#

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.