Amazon Textract, a fully managed machine-learning service, automatically extracts text from scanned documents. It goes beyond optical character recognition (OCR), to identify, understand and extract data from forms or tables.
Today, many companies extract data from scanned documents such as PDF's and tables using manual data entry. This can be slow, expensive, and prone to errors. Or, they use OCR software which requires manual configuration and must be updated every time the form is modified to be usable.
Textract uses machine-learning to automatically read and process any type document. It extracts text, forms, tables, and other data without any manual effort or custom code.
Textract allows you to quickly automate manual document activities and process millions of pages in just hours.