Intelligent OCR Built for Your App

In 2021, Albertsons’ pharmacy technicians were overwhelmed with paper documents. Techs had to manually process a separate patient consent form for every COVID-19 vaccination they performed. Albertsons knew they had to find a better solution. They needed intelligent OCR software.

The first problem was outsourcing to traditional third-party platforms was untenable since they were dealing with their customers’ PII and PHI data. They needed something they could own themselves. The second problem was it needed to work at pop-up vaccination centers, not just in stores or other secure facilities.

The third problem was nobody could help them solve the first two problems.

Every vendor and service provider they reached out to said building the solution they needed as quickly as they needed it was as good as impossible. Everyone offered them the same estimate — four to eight months. But nationwide COVID-19 vaccinations were happening right then, not half a year later.

Then they found Onymos. Using our document digitization suite, the Albertsons VaxConsent app was built and tested in the field in four weeks. Two weeks after that, it was officially live.

OCR vs “Intelligent OCR”

At a high level, you can think of OCR (optical character recognition) as a way to identify and extract data in images.

To get it to work, software developers start by training a neural network to recognize the data you want your OCR technology to find.

That sounds complicated, and in so many ways it is — but if you thought of it as making artificial intelligence look at the same scanned document over and over, then giving it a thumbs up or a thumbs down, depending on if it recognizes a word or not… you wouldn’t be wrong!

Intelligent OCR, sometimes called ICR (intelligent character recognition), is an enhanced form of OCR. Whereas standard OCR produces unstructured data, intelligent OCR generates data that conforms to complex database schemas or other kinds of custom rules. This makes intelligent OCR the archetypal “digital transformation” tool. It can eliminate manual data entry and even fully automate document processing.

A scanning solution in your hand (or on your desk)

Unlike traditional OCR software, Onymos DocKnow is made for you to use in your own app, just like if your team built it themselves. 

Most importantly, it connects directly to your cloud or on-prem infrastructure, so your sensitive business and customer data is never on an Onymos server. We call it “no-data” architecture. It’s why our customers trust using Onymos software in pharmacies, hospitals, and universities. 

On mobile, DocKnow utilizes your device’s photo library and camera for document imaging. On your desktop (or your laptop), it can connect to your scanner. It accepts multiple digital formats and file types: TIFF, PNG, JPEG, PDF, and even multi-page documents.

Plus, it understands any handwriting style (doctors included).

You can also receive an optional, fully customizable UI (meaning access to the actual source code) that displays scanned images of your documents for human-in-the-loop verification.

Digital transformation means digital documents

Whether you need a robust document scanning service for a healthcare use case, like Albertsons, or for invoice processing and record management, like CVS (or for something else entirely), Onymos can help you start automating data extraction. 

• DocKnow is the go-to ICR software for rapid app development and document management. No interim servers and no third-party dashboards. Custom document model training is included, saving time. 

• DocEnhance is for literal digital transformation. Use it to enhance the quality of scanned and photographed documents dramatically. These images can be automatically cropped, skew-corrected, and improved to help them look like they came right from a high-resolution scanner.

• DocID identifies documents on the client side with local machine learning. It’s not just good UX. It’s another layer of protection for your users’ sensitive data.