Real-time Facial Recognition Technology

Fast and lightweight

Low data size and memory usage ensure fast and accurate facial recognition in milliseconds – both online and offline.

Easy to integrate

Integration is a breeze with the detailed guides and samples perfected during more than 10 years of research and development.

Platform & device independant

Face recognition works flawlessly on any device and all major platforms and embedded systems. It works both online and offline, on-client or server-hosted.

Privacy assured

No personal information such as photos or names is stored or processed. This ensures the highest level of privacy, even when dealing with highly sensitive data.

How it works

Facial recognition is based on face descriptors. The system calculates the similarity between the input face descriptor and all face descriptors previously stored in a gallery. The goal is to find the face(s) from the gallery that are most similar to the input face.

  • No images are stored or processed
  • Gallery contains face descriptors and their corresponding names
  • Similarity between faces is returned as a value between 0 (no similarity) and 1 (maximum similarity)


Since all biometric templates are exclusively mathemathical representations of users’ faces, biometric and personal information is strictly separated. This way of handling data ensures the highest level of privacy, even when dealing with extremely sensitive data.
  • Entire software built in-house
  • Biometric templates cannot be exported or reverse-engineered to their original format

Flexible and
easy to integrate

Face recognition is extremely lightweight, which allows it to run smoothly on a wide range of devices, even without an Internet connection.

  • Works online and offline
  • Delivers quick and accurate results
  • Flexible enough to be used for any use case

Ready To Get Started?