Amazon Textract Cheat Sheet

• A fully managed document analysis service for detecting and extracting information from scanned documents.
• Returns extracted data as key-value pairs (e.g., Name: John Doe)
• Supports virtually any type of documents
• Can detect text written in Standard English alphabet and ASCII symbols.
• Mention integration options: works with AWS SDKs (Python, Java, Node.js, etc.), AWS CLI, and Boto3.
• Supports image files (PNG, JPG) and PDFs (single and multipage).
• Can detect handwriting in multiple languages (not just English).
• Works natively with S3 (you can process documents stored in S3 directly).

Common Use Cases:

• Building search indexes
• Importing documents into a business application
• Building automated document processing solutions

• Text extraction for Natural Language Processing (NLP) Applications
• Maintaining document compliance
• Invoice processing: Extract invoice number, date, and total amount automatically.
• Receipt scanning: Automatically categorize expenses for accounting.
• Legal document review: Identify contract clauses, parties, and dates.
• Healthcare forms: Extract patient information and medical codes.
• Data migration: Move data from legacy paper forms into structured databases.

Concepts

• Amazon Textract returns a confidence score for each identified element, which indicates the probability that a given prediction is correct.
• A low-confidence score can be rerouted to Amazon Augmented AI (A2I) for further human review.
• The asynchronous operation allows you to process multipage PDF documents.
• Detect Document Text API
  •  Uses optical character recognition (OCR) technology to extract printed text and handwriting from a document.
• Analyze Document API
  • Extracts printed text, handwriting, and other data from tables and key-value pairs from forms.

APIs

Detect Document Text API:

• Returns all text in the document as LINE and WORD blocks.

• Best for simple text extraction without structure.

Analyze Document API:

• Returns key-value pairs, tables, and forms as structured data.

• Can also return table relationships for easier downstream processing.

• Supports FeatureTypes parameter (["TABLES", "FORMS"]) to control extraction.

New additions:

• StartDocumentTextDetection / StartDocumentAnalysis: asynchronous APIs for large or multipage documents.

• GetDocumentTextDetection / GetDocumentAnalysis: retrieve results for asynchronous operations.

Amazon Textract Pricing

• You only pay for what you use.
• Charges vary for Detect Document Text API and Analyze Document API, with the latter being the more expensive.

Note: If you are studying for the AWS Certified Machine Learning Specialty exam, we highly recommend that you take our AWS Certified Machine Learning – Specialty Practice Exams and read our Machine Learning Specialty exam study guide.

Amazon Textract Cheat Sheet References References:

https://docs.aws.amazon.com/textract/latest/dg/what-is.html
https://docs.aws.amazon.com/textract/latest/dg/textract-best-practices.html
https://aws.amazon.com/blogs/machine-learning/using-amazon-textract-with-amazon-augmented-ai-for-processing-critical-documents/