The .NET OCR SDK supports the Invoice Splitter API.

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

Quick-Start

using Mindee;
using Mindee.Input;
using Mindee.Product.InvoiceSplitter;

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<InvoiceSplitterV1>(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: 15ad7a19-7b75-43d0-b0c6-9a641a12b49b
:Filename: default_sample.pdf

Inference
#########
:Product: mindee/invoice_splitter v1.2
:Rotation applied: No

Prediction
==========
:Invoice Page Groups:
  +--------------------------------------------------------------------------+
  | Page Indexes                                                             |
  +==========================================================================+
  | 0                                                                        |
  +--------------------------------------------------------------------------+
  | 1                                                                        |
  +--------------------------------------------------------------------------+

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.

Specific Fields

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

Invoice Page Groups Field

List of page groups. Each group represents a single invoice within a multi-invoice document.

A InvoiceSplitterV1InvoicePageGroup implements the following attributes:

PageIndexes (List<int>): List of page indexes that belong to the same invoice (group).

Attributes

The following fields are extracted for Invoice Splitter V1:

Invoice Page Groups

InvoicePageGroups(List<InvoiceSplitterV1InvoicePageGroup>): List of page groups. Each group represents a single invoice within a multi-invoice document.

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

Questions?

Join our Slack