Posted On: Dec 1, 2021
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.
- Key- value pairs available on ID’s such as Date of Birth, Date of Issue, ID #, and Restrictions
- Implied fields on the document that may not have explicit keys associated with them such as Name, Address, and Issued By
Additionally, we standardize the key names within the response. For example, if your driver license says LIC# (license number) and passport says Passport No, Analyze ID response will return the standardized key as “Document ID” along with the raw key (e.g. LIC#). This standardization lets customers easily combine information across many IDs that use different terms for the same concept.
To learn more about this new feature you can read a step-by-step blog to get started now or you can view the documentation. Pricing for this new feature is available on Amazon Textract’s pricing page.
Analyze ID will be available US East (N. Virginia), US East (Ohio), US West (Northern California),US West (Oregon), GovCloud (US-East),GovCloud (US-West),Canada (Central), Europe (London), Europe (Paris),Europe (Ireland),Europe (Frankfurt),Asia Pacific (Singapore),Asia Pacific (Sydney),Asia Pacific (Seoul), and Asia Pacific (Mumbai) starting December 1st, 2021. To get started with Analyze ID, visit: http://aws.amazon.com/textract.