Amazon Textract announces specialized support for automated processing of identity documents

Amazon Textract, a machine learning service that makes it easy to extract text and data from any document or image, now offers specialized support to extract data from identity documents, such U.S. Driver Licenses and U.S. Passports. You can extract implied fields like name and address, as well as explicit fields like Date of Birth, Date of Issue, Date of Expiry, ID #, ID Type, and more in the form of key-value pairs. Until today, current OCR based solutions were limited, and did not offer the ability to extract all the required fields accurately due to rich background images or the ability to recognize names and addresses, as well as the fields associated with them (e.g., Washington state ID lists home address with the key “8”), or support ID designs and formats that varied by country or state.

Source:: Amazon AWS