DEV Community

IronSoftware
IronSoftware

Posted on • Originally published at ironsoftware.com

Fast OCR Configuration (Code Example)

This example renders a 35%+ speed improvement over default setup at the cost of 0.2% accuracy.
You may also be interested in how to OCR a specific area within an image that can significantly improve speed.

C#:

var Ocr = new IronTesseract();

// Fast Dictionary
Ocr.Language = OcrLanguage.EnglishFast;

// Latest Engine 
Ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5;

//AI OCR only without font analysis
Ocr.Configuration.EngineMode = TesseractEngineMode.LstmOnly; 

//Turn off unneeded options
Ocr.Configuration.ReadBarCodes = false;
Ocr.Configuration.RenderSearchablePdfsAndHocr = false;

// Assume text is laid out neatly in an orthagonal document
Ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.Auto;

using (var Input = new OcrInput(@"images\image.png"))
{
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}
Enter fullscreen mode Exit fullscreen mode

VB:

Dim Ocr = New IronTesseract()

' Fast Dictionary
Ocr.Language = OcrLanguage.EnglishFast

' Latest Engine 
Ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5

'AI OCR only without font analysis
Ocr.Configuration.EngineMode = TesseractEngineMode.LstmOnly

'Turn off unneeded options
Ocr.Configuration.ReadBarCodes = False
Ocr.Configuration.RenderSearchablePdfsAndHocr = False

' Assume text is laid out neatly in an orthagonal document
Ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.Auto

Using Input = New OcrInput("images\image.png")
    Dim Result = Ocr.Read(Input)
    Console.WriteLine(Result.Text)
End Using
Enter fullscreen mode Exit fullscreen mode

Top comments (0)