Resources

In this demo we demonstrate how two popular document processing tools, Azure AI Document Intelligence and Amazon Textract, handle data extraction from complex documents using ChatGPT to compare and contrast recognition results.

In the demo we use tax forms for testing document processing solutions as tax documents are complex enough to highlight how each intelligent document processing (IDP) solution handles data extraction challenges.

Azure AI Document Intelligence: Pros and Cons

AI Document Intelligence is an AI service that applies advanced machine learning to extract text, key-value pairs, tables, and structures from documents automatically and accurately. You can start with pre-built models, or create your own models tailored to your documents, either locally or in the cloud, using the AI Document Intelligence Studio or SDK.

To extract data with high quality, you need to train your own model using the Azure Document Intelligence toolkit. Training custom models is always free with Document Intelligence. You are only charged when a model is used to analyze a document.

There are significant drawbacks when using Azure Document Intelligence for extracting data from complex documents:

• Microsoft has a pre-built model for generic form extraction, but the quality of work of this model is very questionable for forms outside the list of prebuilt forms. So if you want to get form data out of a document that’s not an English-language receipt, invoice, ID, or business card, you must train a custom model.
• There is no general-purpose fully off-the-shelf service to extract key-value pairs.
• Maximum amount of custom ML models trained per month: 20
• For PDF and TIFF, up to 2000 pages can be processed (with a free tier subscription, only the first two pages are processed).
• Does not extract data from fillable fields.

AWS Textract: Pros and Cons

Textract, an integral component of Amazon Web Services (AWS), stands as a prominent offering within the realm of major cloud providers. Given the vast amounts of data Amazon has access to, their document recognition AI is quite powerful and is able to process reasonably complex documents. 

Despite its widespread use in intelligent document processing systems, there are significant drawbacks to using AWS Textract:

• PDF files are only supported by asynchronous operations; synchronous and asynchronous operations support JPEG, PNG, and TIFF files. Size limits are much higher for asynchronous operations (500MB and 3,000 pages for PDF and TIFF files) than for synchronous operations (10MB, 1 page)
• Amazon Textract supports up to 15 queries per page for synchronous operations and up to 30 queries per page for asynchronous operations
• Cannot classify documents by document type (Passport, Tax Return, Form 1040, Schedule, etc.)
• AWS Textract uses a standard model to extract data from your specific forms. You don't have the ability to further improve and refine the generalized model for your specific form or task.
• Does not extract data from fillable fields.