Receipt recognition settings

Aspose.OCR for .NET allows for very flexible customization of recognition accuracy, performance, and other settings by configuring the properties of the ReceiptRecognitionSettings object.

These settings are applicable when extracting text from scanned receipts in JPEG, PNG, TIFF, BMP, and GIF formats.

Setting	Type	Default value	Description
AllowedCharacters	Aspose.OCR.CharactersAllowedType	Aspose.OCR.CharactersAllowedType.ALL	The predefined whitelist of characters Aspose.OCR engine will look for.
AutoSkew	boolean	true	Automatically correct image tilt (deskew) before proceeding to recognition.
IgnoredCharacters	string	none	A blacklist of characters that are ignored during recognition.
Language	Aspose.OCR.Language	Aspose.OCR.Language.None	Specify a language for recognition.
PreprocessingFilters	Aspose.OCR.Models.PreprocessingFilters.PreprocessingFilter	none	Apply image processing filters that enhance an image before it is sent to the OCR engine.
ThreadsCount	integer	auto	The number of CPU threads used for recognition.
UpscaleSmallFont	boolean	false	Improve small font recognition and detection of dense lines.

Applicable to

• Extracting text from receipts

Example

The following code example shows how to fine-tune receipt recognition:

Aspose.OCR.AsposeOcr recognitionEngine = new Aspose.OCR.AsposeOcr();
Aspose.OCR.ReceiptRecognitionSettings recognitionSettings = new Aspose.OCR.ReceiptRecognitionSettings();
recognitionSettings.AutoSkew = true;
recognitionSettings.Language = Aspose.OCR.Language.Latin;
recognitionSettings.ThreadsCount = 2;
Aspose.OCR.RecognitionResult result = recognitionEngine.RecognizeReceipt("receipt.png", recognitionSettings);
Console.WriteLine(result.RecognitionText);