Receipt OCR .NET

The .NET OCR SDK supports the Receipt API.

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

Quick-Start

using Mindee;
using Mindee.Input;
using Mindee.Product.Receipt;

string apiKey = "my-api-key";
string filePath = "/path/to/the/file.ext";

// Construct a new client
MindeeClient mindeeClient = new MindeeClient(apiKey);

// Load an input source as a path string
// Other input types can be used, as mentioned in the docs
var inputSource = new LocalInputSource(filePath);

// Call the API and parse the input
var response = await mindeeClient
    .ParseAsync<ReceiptV5>(inputSource);

// Print a summary of all the predictions
System.Console.WriteLine(response.Document.ToString());

// Print only the document-level predictions
// System.Console.WriteLine(response.Document.Inference.Prediction.ToString());

You can also call this product asynchronously:

using Mindee;
using Mindee.Input;
using Mindee.Product.Receipt;

string apiKey = "my-api-key";
string filePath = "/path/to/the/file.ext";

// Construct a new client
MindeeClient mindeeClient = new MindeeClient(apiKey);

// Load an input source as a path string
// Other input types can be used, as mentioned in the docs
var inputSource = new LocalInputSource(filePath);

// Call the product asynchronously with auto-polling
var response = await mindeeClient
    .EnqueueAndParseAsync<ReceiptV5>(inputSource);

// Print a summary of all the predictions
System.Console.WriteLine(response.Document.ToString());

// Print only the document-level predictions
// System.Console.WriteLine(response.Document.Inference.Prediction.ToString());

Output (RST):

########
Document
########
:Mindee ID: d96fb043-8fb8-4adc-820c-387aae83376d
:Filename: default_sample.jpg

Inference
#########
:Product: mindee/expense_receipts v5.3
:Rotation applied: Yes

Prediction
==========
:Expense Locale: en-GB; en; GB; GBP;
:Purchase Category: food
:Purchase Subcategory: restaurant
:Document Type: EXPENSE RECEIPT
:Purchase Date: 2016-02-26
:Purchase Time: 15:20
:Total Amount: 10.20
:Total Net: 8.50
:Total Tax: 1.70
:Tip and Gratuity:
:Taxes:
  +---------------+--------+----------+---------------+
  | Base          | Code   | Rate (%) | Amount        |
  +===============+========+==========+===============+
  | 8.50          | VAT    | 20.00    | 1.70          |
  +---------------+--------+----------+---------------+
:Supplier Name: Clachan
:Supplier Company Registrations: Type: VAT NUMBER, Value: 232153895
                                 Type: VAT NUMBER, Value: 232153895
:Supplier Address: 34 Kingley Street W1B 50H
:Supplier Phone Number: 02074940834
:Receipt Number: 54/7500
:Line Items:
  +--------------------------------------+----------+--------------+------------+
  | Description                          | Quantity | Total Amount | Unit Price |
  +======================================+==========+==============+============+
  | Meantime Pale                        | 2.00     | 10.20        |            |
  +--------------------------------------+----------+--------------+------------+

Page Predictions
================

Page 0
------
:Expense Locale: en-GB; en; GB; GBP;
:Purchase Category: food
:Purchase Subcategory: restaurant
:Document Type: EXPENSE RECEIPT
:Purchase Date: 2016-02-26
:Purchase Time: 15:20
:Total Amount: 10.20
:Total Net: 8.50
:Total Tax: 1.70
:Tip and Gratuity:
:Taxes:
  +---------------+--------+----------+---------------+
  | Base          | Code   | Rate (%) | Amount        |
  +===============+========+==========+===============+
  | 8.50          | VAT    | 20.00    | 1.70          |
  +---------------+--------+----------+---------------+
:Supplier Name: Clachan
:Supplier Company Registrations: Type: VAT NUMBER, Value: 232153895
                                 Type: VAT NUMBER, Value: 232153895
:Supplier Address: 34 Kingley Street W1B 50H
:Supplier Phone Number: 02074940834
:Receipt Number: 54/7500
:Line Items:
  +--------------------------------------+----------+--------------+------------+
  | Description                          | Quantity | Total Amount | Unit Price |
  +======================================+==========+==============+============+
  | Meantime Pale                        | 2.00     | 10.20        |            |
  +--------------------------------------+----------+--------------+------------+

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:

  • Confidence (double?): the confidence score of the field prediction.
  • BoundingBox (BoundingBox): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
  • Polygon (Polygon): contains the relative vertices coordinates (Polygon extends List<Point>) of a polygon containing the field in the image.
  • PageId (int?): the ID of the page, always null when at document-level.

Note: A Point simply refers to a List of double.

Aside from the previous attributes, all basic fields have access to a custom ToString method that can be used to print their value as a string.

AmountField

An amount field AmountField extends BaseField, but also implements:

  • Value (double?): corresponds to the field value. Can be null if no value was extracted.

ClassificationField

The classification field ClassificationField extends BaseField, but also implements:

  • Value (strong): corresponds to the field value.

Note: a classification field's value is always a string`.

CompanyRegistration

Aside from the basic BaseField attributes, the company registration field CompanyRegistration also implements the following:

  • Type (string): the type of company.
  • Value (string): corresponds to the field value.
  • ToTableLine(): a method that formats the data to fit in a .rst display.

StringField

The text field StringField extends BaseField, but also implements:

  • Value (string): corresponds to the field value.
  • RawValue (string): corresponds to the raw value as it appears on the document.

DateField

The date field DateField extends StringField, but also implements:

  • DateObject (DateTime?): an accessible representation of the value as a C# object. Can be null.

Locale

The locale field Locale extends BaseField, but also implements:

  • Language (string): ISO 639-1 language code (e.g.: en for English). Can be null.
  • Country (string): ISO 3166-1 alpha-2 or ISO 3166-1 alpha-3 code for countries (e.g.: GRB or GB for "Great Britain"). Can be null.
  • Currency (string): ISO 4217 code for currencies (e.g.: USD for "US Dollars"). Can be null.

Taxes

Tax

Aside from the basic BaseField attributes, the tax field Tax also implements the following:

  • Rate (double?): the tax rate applied to an item expressed as a percentage. Can be null.
  • Code (string): tax code (or equivalent, depending on the origin of the document).
  • Base (double): base amount used for the tax. Can be null.
  • Value (double): the value of the tax. Can be null.

Note: currently Tax is not used on its own, and is accessed through a parent Taxes object, a list-like structure.

Taxes (List)

The Taxes field represents a List of Tax objects. As it is the representation of several objects, it has access to a custom ToString method that can render a Tax object as a table line.

Specific Fields

Fields which are specific to this product; they are not used in any other product.

Line Items Field

List of line item details.

A ReceiptV5LineItem implements the following attributes:

  • Description (string): The item description.
  • Quantity (double): The item quantity.
  • TotalAmount (double): The item total amount.
  • UnitPrice (double): The item unit price.

Attributes

The following fields are extracted for Receipt V5:

Purchase Category

Category: The purchase category among predefined classes.

Possible values include:

  • toll
  • food
  • parking
  • transport
  • accommodation
  • gasoline
  • telecom
  • miscellaneous
System.Console.WriteLine(result.Document.Inference.Prediction.Category.Value);

Purchase Date

Date: The date the purchase was made.

System.Console.WriteLine(result.Document.Inference.Prediction.Date.Value);

Document Type

DocumentType: One of: 'CREDIT CARD RECEIPT', 'EXPENSE RECEIPT'.

Possible values include:

  • expense_receipt
  • credit_card_receipt
System.Console.WriteLine(result.Document.Inference.Prediction.DocumentType.Value);

Line Items

LineItems(List<ReceiptV5LineItem>): List of line item details.

foreach (var LineItemsElem in result.Document.Inference.Prediction.LineItems)
{
    System.Console.WriteLine(LineItemsElem.Value);
}

Expense Locale

Locale: The locale detected on the document.

System.Console.WriteLine(result.Document.Inference.Prediction.Locale.Value);

Receipt Number

ReceiptNumber: The receipt number or identifier.

System.Console.WriteLine(result.Document.Inference.Prediction.ReceiptNumber.Value);

Purchase Subcategory

Subcategory: The purchase subcategory among predefined classes for transport and food.

Possible values include:

  • plane
  • taxi
  • train
  • restaurant
  • shopping
System.Console.WriteLine(result.Document.Inference.Prediction.Subcategory.Value);

Supplier Address

SupplierAddress: The address of the supplier or merchant.

System.Console.WriteLine(result.Document.Inference.Prediction.SupplierAddress.Value);

Supplier Company Registrations

SupplierCompanyRegistrations: List of company registrations associated to the supplier.

foreach (var SupplierCompanyRegistrationsElem in result.Document.Inference.Prediction.SupplierCompanyRegistrations)
{
    System.Console.WriteLine(SupplierCompanyRegistrationsElem.Value);
}

Supplier Name

SupplierName: The name of the supplier or merchant.

System.Console.WriteLine(result.Document.Inference.Prediction.SupplierName.Value);

Supplier Phone Number

SupplierPhoneNumber: The phone number of the supplier or merchant.

System.Console.WriteLine(result.Document.Inference.Prediction.SupplierPhoneNumber.Value);

Taxes

Taxes: List of tax lines information.

foreach (var TaxesElem in result.Document.Inference.Prediction.Taxes)
{
    System.Console.WriteLine(TaxesElem.Value);
}

Purchase Time

Time: The time the purchase was made.

System.Console.WriteLine(result.Document.Inference.Prediction.Time.Value);

Tip and Gratuity

Tip: The total amount of tip and gratuity.

System.Console.WriteLine(result.Document.Inference.Prediction.Tip.Value);

Total Amount

TotalAmount: The total amount paid: includes taxes, discounts, fees, tips, and gratuity.

System.Console.WriteLine(result.Document.Inference.Prediction.TotalAmount.Value);

Total Net

TotalNet: The net amount paid: does not include taxes, fees, and discounts.

System.Console.WriteLine(result.Document.Inference.Prediction.TotalNet.Value);

Total Tax

TotalTax: The total amount of taxes.

System.Console.WriteLine(result.Document.Inference.Prediction.TotalTax.Value);

Questions?

Join our Slack