Amazon Textract announces quality updates to its tables extraction feature
Amazon Textract is a machine learning service that makes it easy to extract text and data from virtually any document. We continuously improve the underlying machine learning models based on customer feedback to provide even better accuracy. Today, we are pleased to announce a quality enhancement to our table recognition feature. Starting today, Textract more accurately detects the outer boundaries, row and column boundaries, and content of tables. The accuracy is especially improved for the tables in receipts and invoices, but you will see improvements across many documents in finance, healthcare, legal, and public sector.
Amazon Textract is a machine learning service that makes it easy to extract text and data from virtually any document. We continuously improve the underlying machine learning models based on customer feedback to provide even better accuracy. Today, we are pleased to announce a quality enhancement to our table recognition feature. Starting today, Textract more accurately detects the outer boundaries, row and column boundaries, and content of tables. The accuracy is especially improved for the tables in receipts and invoices, but you will see improvements across many documents in finance, healthcare, legal, and public sector.
This update will be launched in waves, starting with the Asia Pacific (Sydney), Asia Pacific (Singapore), on April 8th, followed by Europe (Ireland), Europe (Paris), Europe (Frankfurt), Europe (London), Asia Pacific (Seoul), Asia Pacific (Mumbai) on April 12th, followed by Canada (Central), US West (Northern California), US East (Ohio), GovCloud (US-West), GovCloud (US-East) on April 14th, and US East (Northern Virginia), US West (Oregon) on April 15th.