Receipt OCR .NET

The .NET OCR SDK supports the receipt API for extracting data from receipts.

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

Quick Start

// Load a file from disk and parse it

string path = "./ffc127d-sample_receipt.jpeg";
var prediction = await _mindeeClient
    .LoadDocument(File.OpenRead(Path), System.IO.Path.GetFileName(Path))
    .ParseAsync<ReceiptV4Prediction>();

// Print a summary of the parsed data
System.Console.WriteLine(prediction.Inference.Prediction.ToString());

Output:

----- Receipt V4 -----
Filename: 6882f91-receipt23.png
Total amount: 7.27
Total net: 6.86
Tip:
Date: 2022-04-03
Category: food
Subcategory: restaurant
Document type: EXPENSE RECEIPT
Time: 10:00
Supplier name: MINDEE TAKE OUT
Taxes: 0.41 TAX
Total taxes: 0.41
Locale: en-US; en; US; USD;
----------------------

Field Objects

Each Field object contains at a minimum the following attributes:

• Value (string or number depending on the field type):
  Corresponds to the field value. Can be null if no value was extracted.
• Confidence (Float):
  The confidence score of the field prediction.
• Polygon (List<List>):
  Contains the relative vertices coordinates (points) of a polygon containing the field in the image.

Extracted Fields

Attributes that will be extracted from the document and available in the Receipt object:

• Category
• Date
• Locale
• Supplier Information
• Taxes
• Time
• Tip
• Total Amounts

Category

• Category (StringField): Receipt category as seen on the receipt.
  List of supported categories supported: https://developers.mindee.com/docs/receipt-ocr#category.
• SubCategory (StringField): More precise subcategory.
  List of supported subcategories supported: https://developers.mindee.com/docs/receipt-ocr#subcategory.
• DocumentType (StringField): Is a classification field of the receipt.
  The document types supported: https://developers.mindee.com/docs/receipt-ocr#document-type

Date

Date fields:

• contain the raw attribute, which is the textual representation found on the document.
• have a value attribute which is the ISO 8601 representation of the date, regardless of the raw contents.

The following date fields are available:

• Date: Date the receipt was issued

Locale

Locale (Locale): Locale information.

• Locale.Language (String): Language code in ISO 639-1 format as seen on the document.
  The following language codes are supported: ca, de, en, es, fr, it, nl and pt.

• Locale.Currency (String): Currency code in ISO 4217 format as seen on the document.
  The following country codes are supported: CAD, CHF, GBP, EUR, USD.

• Locale.Country (String): Country code in ISO 3166-1 alpha-2 format as seen on the document.
  The following country codes are supported: CA, CH, DE, ES, FR, GB, IT, NL, PT and US.

Supplier Information

• Supplier (StringField): Supplier name as written in the receipt.

Taxes

Taxes (Array< TaxField >): Contains tax fields as seen on the receipt.

• Value (Float): The tax amount.
• Code (String): The tax code (HST, GST... for Canadian; City Tax, State tax for US, etc..).
• Rate (Float): The tax rate.
• basis (Float): The tax base.

Time

• Time: Time of purchase as seen on the receipt
  • Value (string): Time of purchase with 24 hours formatting (hh:mm).
  • Raw (string): In any format as seen on the receipt.

Tip

Tip (AmountField): Total amount of tip and gratuity.

Total Amounts

• TotalAmount (AmountField): Total amount including taxes and tips

• TotalNet (AmountField): Total amount paid excluding taxes and tip

• TotalTax (AmountField): Total tax value from tax lines

 

Questions?
  Join our Slack