How to Find Text with Computer Vision in C#

Why Does IronOCR Require a Separate Computer Vision Package?

Using these methods requires NuGet installation of IronOcr.ComputerVision to the solution. You are prompted to download it if you do not have it installed. The computer vision functionality leverages OpenCV algorithms that significantly enhance text detection accuracy, similar to techniques used in our license plate recognition and passport scanning features.

Which Platform-Specific Package Should I Install?

• Windows: IronOcr.ComputerVision.Windows - See our Windows setup guide
• Linux: IronOcr.ComputerVision.Linux - Check our Linux installation tutorial
• macOS: IronOcr.ComputerVision.MacOS - Review our macOS setup instructions
• macOS ARM: IronOcr.ComputerVision.MacOS.ARM

How Do I Install Using Package Manager Console?

Install using the NuGet Package Manager or paste the following in the Package Manager Console:

Install-Package IronOcr.ComputerVision.Windows

This provides the necessary assemblies to use IronOCR Computer Vision with our model file.

What Is the Basic FindTextRegion Usage?

: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;

How Can I Customize FindTextRegion Parameters?

Call this method with custom parameters to fine-tune text detection. These parameters work similarly to our image filter configurations:

: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;

What Does FindTextRegion Look Like in Practice?

In this example, I use the following image for a method that needs to crop to areas containing text, but input images may vary in text location. I use FindTextRegion to narrow down the scan to an area that Computer Vision has detected text. This approach is similar to techniques used in our content areas and crop regions tutorial. This is an example image:

: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);

How Do I Debug and Verify Text Region Detection?

This code has two outputs. The first is a .png file saved by StampCropRectangleAndSaveAs used for debugging. This technique is also covered in our highlight texts for debugging guide. We can see where IronCV (Computer Vision) detected the text:

The detection accurately identifies the text area. The second output is the text itself:

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

What Is the Basic FindMultipleTextRegions Usage?

: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;

How Can I Customize FindMultipleTextRegions Parameters?

Call this method with custom parameters to control how regions are detected and separated:

: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;

How Do I Process Individual Pages with FindMultipleTextRegions?

Another overload method of FindMultipleTextRegions takes an OCR Page and returns a list of OCR Pages, one for each text region on it. This approach helps when dealing with complex layouts, similar to techniques described in our multipage TIFF processing guide:

: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();

When Should I Use GetTextRegions Instead of FindTextRegion?

/* :path=/static-assets/ocr/content-code-examples/how-to/computer-vision-gettextregions.cs */
using IronOcr;
using IronSoftware.Drawing;
using System;
using System.Collections.Generic;
using System.Linq;

// Create a new IronTesseract object for OCR
var ocr = new IronTesseract();

// Load an image into OcrInput
using var input = new OcrInput();
input.LoadImage("/path/file.png");

// Get the first page from the input
var firstPage = input.GetPages().First();

// Get all text regions detected on this page
List<Rectangle> textRegions = firstPage.GetTextRegions();

// Display information about each detected region
Console.WriteLine($"Found {textRegions.Count} text regions:");
foreach (var region in textRegions)
{
    Console.WriteLine($"Region at X:{region.X}, Y:{region.Y}, Width:{region.Width}, Height:{region.Height}");
}

// You can also process each region individually
foreach (var region in textRegions)
{
    var regionResult = ocr.Read(input, region);
    Console.WriteLine($"Text in region: {regionResult.Text}");
}

/* :path=/static-assets/ocr/content-code-examples/how-to/computer-vision-gettextregions.cs */
using IronOcr;
using IronSoftware.Drawing;
using System;
using System.Collections.Generic;
using System.Linq;

// Create a new IronTesseract object for OCR
var ocr = new IronTesseract();

// Load an image into OcrInput
using var input = new OcrInput();
input.LoadImage("/path/file.png");

// Get the first page from the input
var firstPage = input.GetPages().First();

// Get all text regions detected on this page
List<Rectangle> textRegions = firstPage.GetTextRegions();

// Display information about each detected region
Console.WriteLine($"Found {textRegions.Count} text regions:");
foreach (var region in textRegions)
{
    Console.WriteLine($"Region at X:{region.X}, Y:{region.Y}, Width:{region.Width}, Height:{region.Height}");
}

// You can also process each region individually
foreach (var region in textRegions)
{
    var regionResult = ocr.Read(input, region);
    Console.WriteLine($"Text in region: {regionResult.Text}");
}

What Are Common Use Cases for Computer Vision in OCR?

Computer vision significantly enhances OCR accuracy in challenging scenarios. Here are practical applications:

1. Document Layout Analysis: Identify and process different sections of complex documents automatically. Especially useful with scanned documents.

2. Multi-Column Text: Separate and read columns independently for newspapers or magazines. Use multithreaded processing for faster results.

3. Mixed Content: Distinguish between text regions and graphics in documents. Helpful when processing photos with embedded text.

4. Performance Optimization: Focus OCR processing only on text-containing areas. See our fast OCR configuration guide.

5. Quality Control: Verify text detection before full OCR processing. Our progress tracking feature monitors each stage.

With the right settings and input files, OCR can achieve near-human reading capability. For optimal results, combine computer vision with our image optimization filters to achieve the best possible OCR accuracy. When working with low-quality images, our guide on fixing low quality scans provides valuable preprocessing techniques.

Advanced Computer Vision Techniques

For developers looking to push OCR accuracy boundaries, consider these advanced approaches:

• Custom Training: Train the OCR engine for specialized fonts using our custom language files guide
• Multi-Language Support: Process multi-language documents with our multiple languages feature
• Barcode Integration: Combine text recognition with barcode reading using our OCR with barcode reading capabilities