Evaluate your use case

Before processing documents in Document Automation, you must ensure that your documents are Standard Forms. After you confirm that your document meets the prescribed Standard Forms criteria, you can proceed with the type of extraction service required.

To determine if your use case meets the Standard Forms criteria, review the following parameters:
  • The layout of your document remains the same across vendors.
  • The positions of various data elements such as checkboxes, tables, and so on, is fixed in your documents.
  • You have documents where the values are independent of other data elements.
  • Your document is available in a supported language. For more information, see Azure Form Recognizer Supported Languages.
  • Your documents contain tables that have the same number of rows and columns.
  • The document layout remains the same within the same year, across different organizations.

Review extraction service

After you have confirmed that the documents are Standard Forms, you can then plan the type of standard forms extraction service that fits your requirement. You can use the Microsoft Form Recognizer service to process Standard Forms in Document Automation. Before processing, ensure the following:

  • Input documents can contain:
    • Information with many details and have a reasonable quality resolution (>200 dpi)
    • Check-boxes and radio buttons
    • Handwritten content
    • Signatures
    • Tables
      Note: Input documents can also contain tables that span over a single page. However, if the Standard Forms contain table that spans across multiple pages, the content extraction can fail.
  • No section of the input document is repeated.
  • Documents that contain transpose tables.

Benefits of Microsoft Azure Forms Recognizer service

  • Ability to process diverse standard form type documents.
  • Auto detection feature can identify different types of tables, such as header-less tables, inverted tables, and so on.
  • Provides good support for handwritten forms.