Documents recognition as easy as reading two bytes.
If you have any problems with or questions about this client, please contact us through a GitHub issue. You are invited to contribute new features, fixes, or updates, large or small; We are always thrilled to receive pull requests, and do our best to process them as fast as we can. See dev guide
regula.documentreader.webclient
is on the Python Package Index (PyPI):
pip install regula.documentreader.webclient
Or using pipenv
pipenv install regula.documentreader.webclient
Performing request:
from regula.documentreader.webclient import *
with open("australia_passport.jpg", "rb") as f:
input_image = f.read()
with DocumentReaderApi(host='http://localhost:8080') as api:
params = ProcessParams(
scenario=Scenario.FULL_PROCESS,
result_type_output=[Result.DOCUMENT_IMAGE, Result.STATUS, Result.TEXT, Result.IMAGES]
)
request = RecognitionRequest(process_params=params, images=[input_image])
response = api.process(request)
Parsing results:
# status examples
response_status = response.status
doc_overall_status = "valid" if response_status.overall_status == CheckResult.OK else "not valid"
# text fields example
doc_number_field = response.text.get_field(TextFieldType.DOCUMENT_NUMBER)
doc_number_mrz = doc_number_field.get_value()
doc_number_visual = doc_number_field.get_value(Source.VISUAL)
doc_number_visual_validity = doc_number_field.source_validity(Source.VISUAL)
doc_number_mrz_validity = doc_number_field.source_validity(Source.MRZ)
doc_number_mrz_visual_matching = doc_number_field.cross_source_comparison(Source.MRZ, Source.VISUAL)
# images fields example
normalized_input_image = response.images.document_image()
portrait_field = response.images.get_field(GraphicFieldType.PORTRAIT)
portrait_from_visual = portrait_field.get_value(Source.VISUAL)
portrait_from_rfid = portrait_field.get_value(Source.RFID, original=True)
You can find more detailed guide and run this sample in example folder.