OCRProcessor Class

Represents a logic to process OCR for the Loaded PDF document.

Inheritance

System.Object

OCRProcessor

Implements

System.IDisposable

Namespace: Syncfusion.OCRProcessor

Assembly: Syncfusion.OCRProcessor.Base.dll

Syntax

public class OCRProcessor : Object, IDisposable

Constructors

OCRProcessor()

Initializes a new instance of the class.

Declaration

public OCRProcessor()

OCRProcessor(String)

Initializes a new instance of the OCRProcessor class with the specified tesseract binary file path.

Declaration

public OCRProcessor(string tesseractPath)

Parameters

Type	Name	Description
System.String	tesseractPath	Tesseract binary path.

Properties

ExternalEngine

Sets the external OCR engine to perform the OCR on a PDF or Image.

Declaration

public IOcrEngine ExternalEngine { set; }

Property Value

Type
IOcrEngine

Examples

// Initialize the OCR processor.
OCRProcessor processor = new OCRProcessor();
//loading the input image.
FileStream stream = new FileStream(@"Input.pdf", FileMode.Open);
PdfLoadedDocument document = new PdfLoadedDocument(stream);
//Create custom OCR engine to process the OCR. 
IOcrEngine azureOcrEngine = new AzureExternalOcrEngine();
//Set external OCR engine.
processor.ExternalEngine = azureOcrEngine;
document = processor.PerformOCR(document);
 FileStream outputStream = new FileStream("Output.pdf", FileMode.CreateNew);
//Save the document into stream.
document.Save(outputStream);
document.Close(true);

ImageEnhancementMode

Gets or sets the image enhancement mode used for OCR processor

Declaration

public OcrImageEnhancementMode ImageEnhancementMode { get; set; }

Property Value

Type
OcrImageEnhancementMode

Examples

// Initialize the OCR processor.
OCRProcessor processor = new OCRProcessor();
//loading the input image.
FileStream stream = new FileStream(@"Input.pdf", FileMode.Open);
PdfLoadedDocument document = new PdfLoadedDocument(stream);
sets the image enhancement mode used for OCR processor
processor.ImageEnhancementMode = OcrImageEnhancementMode.EnhanceForRecognitionOnly;
document = processor.PerformOCR(document);
FileStream outputStream = new FileStream("Output.pdf", FileMode.CreateNew);
//Save the document into stream.
document.Save(outputStream);
document.Close(true);

ImageProcessor

Gets or sets the image processor used by the OCR processor

Declaration

public IImageProcessor ImageProcessor { get; set; }

Property Value

Type
IImageProcessor

Examples

// Initialize the OCR processor.
OCRProcessor processor = new OCRProcessor();
//loading the input image.
FileStream stream = new FileStream(@"Input.pdf", FileMode.Open);
PdfLoadedDocument document = new PdfLoadedDocument(stream);
sets the image processor used by the OCR processor
processor.ImageProcessor = new ImageProcessor();
document = processor.PerformOCR(document);
FileStream outputStream = new FileStream("Output.pdf", FileMode.CreateNew);
//Save the document into stream.
document.Save(outputStream);
document.Close(true);

Settings

Gets or sets the OCR settings to a document.

Declaration

public OCRSettings Settings { get; set; }

Property Value

Type
OCRSettings

See Also

OCRSettings

TessDataPath

Gets or sets the tessdata folder path to process the OCR.

Declaration

public string TessDataPath { get; set; }

Property Value

Type
System.String

Examples

// Initialize the OCR processor
OCRProcessor processor = new OCRProcessor();
//loading the input image
FileStream stream = new FileStream(@"Input.jpeg ", FileMode.Open);
Bitmap image = new Bitmap(stream);
// Set OCR language to process
processor.Settings.Language = Languages.English;
FileStream fontStream = new FileStream(@"ARIALUNI.ttf", FileMode.Open);
processor.UnicodeFont = new PdfTrueTypeFont(fontStream, true, PdfFontStyle.Regular, 10);
processor.Settings.Conformance = PdfConformanceLevel.Pdf_A1B;
processor.TesseractPath = TesseractBinariesPath;
processor.TessDataPath = TessdataPath;
PdfDocument document = processor.PerformOCR(image);
document.Save("Output.pdf");
document.Close(true);

TesseractPath

Gets or sets the Tesseractbinaries folder path to process the OCR.

Declaration

public string TesseractPath { get; set; }

Property Value

Type
System.String

Examples

// Initialize the OCR processor
OCRProcessor processor = new OCRProcessor();
//loading the input image
FileStream stream = new FileStream(@"Input.jpeg ", FileMode.Open);
Bitmap image = new Bitmap(stream);
// Set OCR language to process
processor.Settings.Language = Languages.English;
FileStream fontStream = new FileStream(@"ARIALUNI.ttf", FileMode.Open);
processor.UnicodeFont = new PdfTrueTypeFont(fontStream, true, PdfFontStyle.Regular, 10);
processor.Settings.Conformance = PdfConformanceLevel.Pdf_A1B;
processor.TesseractPath = TesseractBinariesPath;
processor.TessDataPath = TessdataPath;
PdfDocument document = processor.PerformOCR(image);
document.Save("Output.pdf");
document.Close(true);

UnicodeFont

Sets Unicode font to preserve the Unicode characters in a PDF document.

Declaration

public PdfTrueTypeFont UnicodeFont { set; }

Property Value

Type
PdfTrueTypeFont

See Also

PdfTrueTypeFont

Methods

CompressJPEGImage(Image)

Declaration

public Image CompressJPEGImage(Image bmp1)

Parameters

Type	Name	Description
System.Drawing.Image	bmp1

Returns

Type
System.Drawing.Image

Dispose()

Releases the unmanaged and optionally managed resources.

Declaration

public void Dispose()

Finalize()

Releases unmanaged resources and performs other cleanup operations before the OCRProcessor is reclaimed by garbage collection.

Declaration

protected override void Finalize()

PerformOCR(PdfLoadedDocument)

Perform the OCR on a PDF document.

Declaration

public string PerformOCR(PdfLoadedDocument lDoc)

Parameters

Type	Name	Description
PdfLoadedDocument	lDoc	PdfLoadedDocument

Returns

Type	Description
System.String	Returns the OCRed texts

Examples

// Initialize the OCR processor.
OCRProcessor processor = new OCRProcessor();
//loading the input image.
FileStream stream = new FileStream(@"Input.pdf", FileMode.Open);
PdfLoadedDocument document = new PdfLoadedDocument(stream);
document = processor.PerformOCR(document);
 FileStream outputStream = new FileStream("Output.pdf", FileMode.CreateNew);
//Save the document into stream.
document.Save(outputStream);
document.Close(true);

PerformOCR(PdfLoadedDocument, Int32, Int32, String)

Perform the OCR process for a PdfLoadedDocument.

Declaration

public string PerformOCR(PdfLoadedDocument lDoc, int startIndex, int endIndex, string dataPath)

Parameters

Type	Name	Description
PdfLoadedDocument	lDoc	PdfLoadedDocument
System.Int32	startIndex	The number that is use as a start point for the OCR process.
System.Int32	endIndex	The number that is use as a end point for the OCR process.
System.String	dataPath	Tesseract data path

Returns

Type	Description
System.String	Returns the OCRed texts

PerformOCR(PdfLoadedDocument, Int32, Int32, String, out OCRLayoutResult)

Perform the OCR process for a PdfLoadedDocument.

Declaration

public string PerformOCR(PdfLoadedDocument lDoc, int startIndex, int endIndex, string dataPath, out OCRLayoutResult hocrBounds)

Parameters

Type	Name	Description
PdfLoadedDocument	lDoc	PdfLoadedDocument
System.Int32	startIndex	The number that is use as a start point for the OCR process.
System.Int32	endIndex	The number that is use as a end point for the OCR process.
System.String	dataPath	Tesseract data path
OCRLayoutResult	hocrBounds	When this method returns, Layout result of the OCR'ed document

Returns

Type	Description
System.String	Returns the OCRed texts

PerformOCR(PdfLoadedDocument, String)

Perform the OCR process for a PdfLoadedDocument.

Declaration

public string PerformOCR(PdfLoadedDocument lDoc, string dataPath)

Parameters

Type	Name	Description
PdfLoadedDocument	lDoc	PdfLoadedDocument
System.String	dataPath	Tesseract data path

Returns

Type	Description
System.String	Returns the OCRed texts

PerformOCR(PdfLoadedDocument, String, out OCRLayoutResult)

Perform the OCR process for a PdfLoadedDocument.

Declaration

public string PerformOCR(PdfLoadedDocument lDoc, string dataPath, out OCRLayoutResult hocrBounds)

Parameters

Type	Name	Description
PdfLoadedDocument	lDoc	PdfLoadedDocument
System.String	dataPath	Tesseract data path
OCRLayoutResult	hocrBounds	When this method returns, Layout result of the OCR'ed document

Returns

Type	Description
System.String	Returns the OCRed texts

PerformOCR(Bitmap, String)

Declaration

public string PerformOCR(Bitmap img, string dataPath)

Parameters

Type	Name	Description
System.Drawing.Bitmap	img
System.String	dataPath

Returns

Type
System.String

PerformOCR(Bitmap, String, out OCRLayoutResult)

Perform the OCR process for an image.

Declaration

public string PerformOCR(Bitmap img, string dataPath, out OCRLayoutResult hocrBounds)

Parameters

Type	Name	Description
System.Drawing.Bitmap	img	Source image to process OCR.
System.String	dataPath	Tesseract data path
OCRLayoutResult	hocrBounds	When this method returns, Layout results of the OCR'ed image

Returns

Type	Description
System.String	Returns the OCRed texts

PerformOCR(Stream)

Perform OCR on the image stream and create a searchable PDF document.

Declaration

public PdfDocument PerformOCR(Stream imgStream)

Parameters

Type	Name	Description
System.IO.Stream	imgStream	Source image to process OCR.

Returns

Type	Description
PdfDocument	Returns the OCRed texts in Pdfdocument

Examples

// Initialize the OCR processor.
OCRProcessor processor = new OCRProcessor();
//loading the input image.
FileStream image = new FileStream(@"Input.jpeg ", FileMode.Open);
// Set OCR language to process.
processor.Settings.Language = Languages.English;
FileStream fontStream = new FileStream(@"ARIALUNI.ttf", FileMode.Open);
processor.UnicodeFont = new PdfTrueTypeFont(fontStream, true, PdfFontStyle.Regular, 10);
processor.Settings.Conformance = PdfConformanceLevel.Pdf_A1B;
processor.TesseractPath = TesseractBinariesPath;
processor.TessDataPath = TessdataPath;
PdfDocument document = processor.PerformOCR(image);
document.Save("Output.pdf");
document.Close(true);

Implements

System.IDisposable