Posted On: Jul 8, 2021

Amazon Textract is a machine learning service that automatically extracts text, handwriting and data from scanned documents that goes beyond simple optical character recognition (OCR) to identify, understand, and extract data from forms and tables. We continuously improve the underlying machine learning models based on your feedback to provide even better accuracy. Today, we are pleased to announce an accuracy enhancement update to the handwriting extraction feature. Starting today, you will see improved accuracy of handwritten transcriptions, specifically for numerals, dates, phone numbers, and website address across many documents in finance, healthcare, legal, public sector, and others. Textract now more accurately detects handwriting within documents such as checks, medical forms, travel forms and more. 

This update will be launched in waves, starting with the Asia Pacific (Singapore) region on July 8th, followed by US West (Northern California), Europe (Ireland), Asia Pacific (Sydney), US East (Ohio) on July 9th, Europe (Frankfurt), GovCloud (US-West), GovCloud (US-East), US East (Northern Virginia), Europe (London) on July 12th, and Europe (Paris), Asia Pacific (Seoul), Canada (Central), Asia Pacific (Mumbai) and US West (Oregon) on July 13th.