Business Card OCR Python
The Python OCR SDK supports the Business Card API.
Using the sample below, we are going to illustrate how to extract the data that we want using the OCR SDK.
Quick-Start
from mindee import Client, product, AsyncPredictResponse
# Init a new client
mindee_client = Client(api_key="my-api-key")
# Load a file from disk
input_doc = mindee_client.source_from_path("/path/to/the/file.ext")
# Load a file from disk and enqueue it.
result: AsyncPredictResponse = mindee_client.enqueue_and_parse(
product.BusinessCardV1,
input_doc,
)
# Print a brief summary of the parsed data
print(result.document)
Output (RST):
########
Document
########
:Mindee ID: 6f9a261f-7609-4687-9af0-46a45156566e
:Filename: default_sample.jpg
Inference
#########
:Product: mindee/business_card v1.0
:Rotation applied: Yes
Prediction
==========
:Firstname: Andrew
:Lastname: Morin
:Job Title: Founder & CEO
:Company: RemoteGlobal
:Email: [email protected]
:Phone Number: +14015555555
:Mobile Number: +13015555555
:Fax Number: +14015555556
:Address: 178 Main Avenue, Providence, RI 02111
:Website: www.remoteglobalconsulting.com
:Social Media: https://www.linkedin.com/in/johndoe
https://twitter.com/johndoe
Field Types
Standard Fields
These fields are generic and used in several products.
BaseField
Each prediction object contains a set of fields that inherit from the generic BaseField
class.
A typical BaseField
object will have the following attributes:
- value (
Union[float, str]
): corresponds to the field value. Can beNone
if no value was extracted. - confidence (
float
): the confidence score of the field prediction. - bounding_box (
[Point, Point, Point, Point]
): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document. - polygon (
List[Point]
): contains the relative vertices coordinates (Point
) of a polygon containing the field in the image. - page_id (
int
): the ID of the page, alwaysNone
when at document-level. - reconstructed (
bool
): indicates whether an object was reconstructed (not extracted as the API gave it).
Note: A
Point
simply refers to a List of two numbers ([float, float]
).
Aside from the previous attributes, all basic fields have access to a custom __str__
method that can be used to print their value as a string.
StringField
The text field StringField
only has one constraint: its value is an Optional[str]
.
Attributes
The following fields are extracted for Business Card V1:
Address
address (StringField): The address of the person.
print(result.document.inference.prediction.address.value)
Company
company (StringField): The company the person works for.
print(result.document.inference.prediction.company.value)
Email
email (StringField): The email address of the person.
print(result.document.inference.prediction.email.value)
Fax Number
fax_number (StringField): The Fax number of the person.
print(result.document.inference.prediction.fax_number.value)
Firstname
firstname (StringField): The given name of the person.
print(result.document.inference.prediction.firstname.value)
Job Title
job_title (StringField): The job title of the person.
print(result.document.inference.prediction.job_title.value)
Lastname
lastname (StringField): The lastname of the person.
print(result.document.inference.prediction.lastname.value)
Mobile Number
mobile_number (StringField): The mobile number of the person.
print(result.document.inference.prediction.mobile_number.value)
Phone Number
phone_number (StringField): The phone number of the person.
print(result.document.inference.prediction.phone_number.value)
Social Media
social_media (List[StringField]): The social media profiles of the person or company.
for social_media_elem in result.document.inference.prediction.social_media:
print(social_media_elem.value)
Website
website (StringField): The website of the person or company.
print(result.document.inference.prediction.website.value)
Questions?
Updated 17 days ago