New Partnership Announcement: Nanonets

A year ago this month (27/04/2022), we released a blog post comparing the Optical Character Recognition aka OCR (Extracting data from PDFs and images!) software of some of the biggest tech companies around the world - Google, Amazon and Microsoft (Due to the rapidly progressing nature of technology, it has all improved by many, many times). They were all outperformed by an Intelligent OCR software called Nanonets!

At Continuum we only want the best for our clients which is why today we are delighted to announce we are partnering with Nanonets!

Intelligent OCR

Unlike traditional OCR technology which will bulk parse out (analyse) structured text, Nanonets removes these set templates and requirements for structured PDFs and instead promotes you to build models so it can pick out the relevant information you need. When you give Nanonets some unseen production data it will magically pull out the desired fields. It really is a “wow moment” when you first see it in action and these dynamically named or positioned fields are recognized and perfectly read by the Nanonets software.

Some great use cases we have looked at are:

> Extracting KYC data from passports, licenses and utility documents.

> Identifying and parsing all tabular data from a series of PDFs.

> Pulling required data from invoices from multiple supplier formats.

The first step for us was integrating Nanonets with Alteryx. We now have a seamless passing of images or files to Nanonets and returning the structured data back into Alteryx to carry on with your data processes. If you would like to hear more about extracting data from your PDFs or images please do not hesitate to get in touch!