Receipt recognition settings
Aspose.OCR for Python via .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 |
---|---|---|---|
allowed_symbols |
string |
All characters of the selected language | The whitelist of characters Aspose.OCR engine will look for. |
ignored_symbols |
string | none | A blacklist of characters that are ignored during recognition. |
language |
Language | Language.NONE |
Specify a language for recognition. |
upscale_small_font |
boolean | false |
Improve small font recognition and detection of dense lines. |
automatic_color_inversion |
boolean | true |
Improve recognition accuracy of white text on a dark/black background. If you are not optimizing every aspect of recognition (for example, for online applications or entry-level devices), leave this setting set to true. |
threads_count |
integer | auto | The number of CPU threads used for recognition. |
Applicable to
Example
The following code example shows how to fine-tune receipt recognition:
# Instantiate Aspose.OCR API
api = AsposeOcr()
# Add images to the recognition batch
input = OcrInput(InputType.SINGLE_IMAGE)
input.add("car1.png")
input.add("car2.png")
# Customize recognition settings
recognitionSettings = ReceiptRecognitionSettings()
recognitionSettings.language = Language.LATIN
# Recognize receipts
result = api.recognize_receipt(input, recognitionSettings)
# Print recognition result
print(result[0].recognition_text)
input("Press Enter to continue...")