Subscribe to Impira's blog
Stay up to date with all things Impira, automation, document processing, and industry best practices.
Most documents that our customers work with are actually tables. Even things like invoices, loss run reports, and purchase orders have a table element to them. And while machine learning algorithms love a tidy table, messy tables or tables with varying row heights are a bit more challenging to automate an extraction from.
Below, we have a table with variable height rows
Machine learning templates don't account for this type of varied height for rows. So we wanted to build something that truly understands when data belongs together in a cell or row and not rely on predetermined borders.
See it in action
Okay, now you know a little bit about the functionality, let’s just go ahead and show you how it works on a real document. Check out the video below.
Try it on your invoices and purchase orders
Ready to see how easy it can be to automate your data extraction process? With a few clicks, you can set up your own custom machine learning model for free.
Try Impira today and start making data entry a thing of the past.