Leverage OCR and Machine Learning Technologies

Let’s cover the basics first- 

If you are not already familiar, Optical Character Recognition, also known as OCR, is an electronic or mechanical conversion of images of typed, handwritten, or printed text into encoded text. OCR images can come from a photo, scanned documents, etc. Essentially OCR technology converts images to character text so that your computer is able to read it. 

We use OCR technology in our everyday lives without really knowing:

  • Ever deposited a check over your mobile banking app by taking a photo of a check? Banks use OCR technology to extract text from the photo you took on your phone’s camera.

  • Ever traveled internationally? Your passport contains something called machine-readable zones or MRZ that when scanned, extracts and presents data to make border checkpoints faster and more accurate. 

  • Ever use coupons when shopping or scan a QR code (that matrix looking box)? When the square is scanned or photographed it automatically reads and registers the information to follow a prompt, in a coupon example, a percent or dollar amount is automatically taken off.

  • Ever get mail? Well, USPS uses OCR to analyze the text on letters to sort mail to be delivered to your mailbox. 

All of those are simple applications of the technology that make our lives so much easier. But when you take OCR and apply it with other technologies, such as machine learning, it can be much more powerful, and that is exactly what we have done here at Extract.  

Our intelligent redaction software, ID Shield, uses algorithms and advanced data extraction to ‘read’ OCR’s text. Based on your wants and needs, we create a ruleset designed to fit your documents so that the OCR’d text is automatically validated. Basically, it finds key terms and private information, applies a secure redaction to the documents, and outputs to any format required by your system. 

What are the benefits of our platform?

  • Facilitates open access to public record requests

  • Allows you to reallocate staff, or allow staff to work remotely 

  • Minimizes cost, time, and effort of indexing and redacting records

  • Ensures online records comply with data privacy laws. 

 Interested in learning more about what we offer? Check out a few case studies here. Or reach out today for a demo.


About the Author: Taylor Genter   Taylor is the Marketing Specialist at Extract with experience in data analytics, graphic design, and both digital and social media marketing.  She earned her Bachelor of Business Administration degree in Marketing at the University of Wisconsin- Whitewater. Taylor enjoys analyzing people’s behaviors and attitudes to find out what motivates them, and then curating better ways to communicate with them.