US W9 OCR Python

The Python OCR SDK supports the W9 API.

Using the sample below, we are going to illustrate how to extract the data that we want using the OCR SDK.
W9 sample


from mindee import Client, PredictResponse, product

# 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 parse it.
# The endpoint name must be specified since it cannot be determined from the class.
result: PredictResponse = mindee_client.parse(, input_doc)

# Print a summary of the API result

# Print the document-level summary
# print(result.document.inference.prediction)

Output (RST):

:Mindee ID: d7c5b25f-e0d3-4491-af54-6183afa1aaab
:Filename: default_sample.jpg

:Product: mindee/us_w9 v1.0
:Rotation applied: Yes


Page Predictions

Page 0
:Name: Stephen W Hawking
:SSN: 560758145
:Address: Somewhere In Milky Way
:City State Zip: Probably Still At Cambridge P O Box CB1
:Business Name:
:EIN: 942203664
:Tax Classification: individual
:Tax Classification Other Details:
:W9 Revision Date: august 2013
:Signature Position: Polygon with 4 points.
:Signature Date Position:
:Tax Classification LLC:

Field Types

Standard Fields

These fields are generic and used in several products.


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 be None 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, is None 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.


The position field PositionField does not implement all the basic BaseField attributes, only bounding_box, polygon and page_id. On top of these, it has access to:

  • rectangle ([Point, Point, Point, Point]): a Polygon with four points that may be oriented (even beyond canvas).
  • quadrangle ([Point, Point, Point, Point]): a free polygon made up of four points.


The text field StringField only has one constraint: its value is an Optional[str].

Page-Level Fields

Some fields are constrained to the page level, and so will not be retrievable to through the document.


The following fields are extracted for W9 V1:


šŸ“„address (StringField): The street address (number, street, and apt. or suite no.) of the applicant.

for address_elem in result.document.address:

Business Name

šŸ“„business_name (StringField): The business name or disregarded entity name, if different from Name.

for business_name_elem in result.document.business_name:

City State Zip

šŸ“„city_state_zip (StringField): The city, state, and ZIP code of the applicant.

for city_state_zip_elem in result.document.city_state_zip:


šŸ“„ein (StringField): The employer identification number.

for ein_elem in result.document.ein:


šŸ“„name (StringField): Name as shown on the applicant's income tax return.

for name_elem in

Signature Date Position

šŸ“„signature_date_position (PositionField): Position of the signature date on the document.

for signature_date_position_elem in result.document.signature_date_position:

Signature Position

šŸ“„signature_position (PositionField): Position of the signature on the document.

for signature_position_elem in result.document.signature_position:


šŸ“„ssn (StringField): The applicant's social security number.

for ssn_elem in result.document.ssn:

Tax Classification

šŸ“„tax_classification (StringField): The federal tax classification, which can vary depending on the revision date.

for tax_classification_elem in result.document.tax_classification:

Tax Classification LLC

šŸ“„tax_classification_llc (StringField): Depending on revision year, among S, C, P or D for Limited Liability Company Classification.

for tax_classification_llc_elem in result.document.tax_classification_llc:

Tax Classification Other Details

šŸ“„tax_classification_other_details (StringField): Tax Classification Other Details.

for tax_classification_other_details_elem in result.document.tax_classification_other_details:

W9 Revision Date

šŸ“„w9_revision_date (StringField): The Revision month and year of the W9 form.

for w9_revision_date_elem in result.document.w9_revision_date:


Join our Slack