Passport recognition settings

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

These settings are specifically tailored for processing scanned or photographed passports.

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.
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.
country	Country	Country.UNIVERSAL	Extract key passport details (such as a number, name, date of birth, and so on) for the specific country in addition to the entire passport text. See Supported countries section below.

Supported countries

A list of countries for retrieving specific details (such as a number, name, date of birth, and so on) from passport images:

Value	Country
Country.UNIVERSAL	Do not parse passport details (only recognize passport text).
Country.MADAGASCAR	Parse Malagasy passports.

Applicable to

• Extracting text from a passport

Example

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

# Instantiate Aspose.OCR API
api = AsposeOcr()
# Add images to the recognition batch
input = OcrInput(InputType.SINGLE_IMAGE)
input.add("passport1.png")
input.add("passport2.png")
# Customize recognition settings
recognitionSettings = PassportRecognitionSettings()
recognitionSettings.language = Language.LATIN
# Recognize passports
result = api.recognize_passport(input, recognitionSettings)
# Print recognition result
print(result[0].recognition_text)
input("Press Enter to continue...")