Skip to main content

Update a Check

PUT 

/api/v8/partner/checks/:document_id

Veryfi's Update a Document by ID endpoint allows you to change a Document that Veryfi's Machine Learning models have already processed. This feature will enable users to update Documents previously processed by Veryfi to ensure data extraction accuracy. Updating a Document is especially useful for correcting mistakes and updating information over time. By changing a processed Document, Veryfi's Machine Learning models can re-learn the updated information, allowing them to stay accurate and up-to-date.

Request

Path Parameters

    document_id int64required

    The unique identifier of the document.

Body

    anyOf
    amount object
    value numberrequired

    Possible values: > 0

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    amount_text object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bank_address object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bank_name object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    micr object
    routing_number object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    account_number object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    serial_number object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    raw object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    check_number object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    date object
    value daterequired
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    memo object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    payer_address object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    payer_name object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    receiver_address object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    receiver_name object
    value stringrequired

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

Responses

A processed Check response.

Schema
    anyOf
    pdf_url uri

    Possible values: non-empty and <= 2083 characters

    A signed URL to access the auto-generated PDF created from the submitted document. This URL expires 15 minutes after the response object is returned and is resigned during every GET request.

    id integerrequired

    The unique number created to identify the document.

    text stringrequired

    The text returned from converting the document into a machine-readable text format.

    amount object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value numberrequired

    Possible values: > 0

    amount_text object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    bank_address object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    bank_name object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    fractional_routing_number object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    routing_from_fractional object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    micr object
    routing_number objectrequired

    The bank routing number.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    account_number objectrequired

    The bank account number.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    serial_number objectrequired

    The serial number on personal checks.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    raw objectrequired

    The text returned from converting the document into a machine-readable text format.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    check_number object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    date object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value daterequired
    memo object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    payer_address object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    payer_name object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    receiver_address object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

    receiver_name object
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    ocr_score number

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    score number

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    rotation integer

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value stringrequired

    Possible values: non-empty

    The extracted value.

Loading...