Use case
The client, a provider of biometrics solutions for governments and enterprises, wanted to extend the functionality of their existing product. They needed to read and extract information from different countries´ ID cards and documents. Knowing about our core machine vision expertise, they came talking to us.
Solution
We have developed a highly reliable OCR (Optical characters recognition) engine that is able to read various IDs and documents from different countries. We designed it in a way that would make it easy to onboard new documents and cards and extract the needed information from them.
Highly robust to cope with real world conditions, yet requiring only zero to several training images to be production-ready. All thanks to our AI secret sauce.
Result
The client didn’t have to build an internal machine vision expertise. They outsourced it to us, which gave them more space to focus on their core product. As a result, they acquired an important functionality which increased perceived value of their existing solution enabling them to expand to new markets and business verticals.
Daniel Ferak
Head of DOT TeamImpact
Acquisition of important functionality increasing perceived value of their existing solution and enablement to expand to new markets and business verticals.
Tags
- API
- Language
- OCR
- Scale-ups
- Segmentation
- Synthetic Data