Our Technology Stack

State-of-the-art, trusted and versatile

Object Detection using Convolutional Neural Networks

Image and Video Anonymization with Deep Learning

Schematic depiction of Mask R-CNN.

Our core technology is object detection using deep convolutional networks (CNN), which in recent years has rapidly evolved from an academic playground to production-ready tools for solving industrial use cases fast and effectively.

We combine different architectures such as instance segmentation (Mask R-CNN[1] with a FPN backbone[2]) and keypoint detection (based on Faster R-CNN[3]) to anonymize people, vehicles, faces or licence plates.

As part of the NVIDIA Inception program for AI startups, we have access to support, expertise and training by NVIDIA, the leading AI hardware manufacturer.

Cloud, Docker and APIs

Scalable and Flexible Anonymization Pipeline

We have set up our scalable and flexible anonymization pipelines in GDPR-compliant data centres around Europe. Available also as a Docker container, it can be installed on a local machine, private or public cloud infrastructure.


Amazon Web Services



Frequently Asked Questions

Let us help answer the most common questions you might have

How can I optimize for throughput?

You can run multiple containers per GPU or utilize multiple GPUs.

What happens to the metadata of the original image (e.g. GPS coordinates)?

Metadata (e.g. EXIF information & ICC colour profile) is retained when creating the anonymized version of an image. Also, we can generate segmentation mask files per processed image.

Can the anonymization (blurring) be reversed?

Our solution applies a non-linear median blur multiple times with different kernel sizes. Due to the high loss of pixel information, de-anonymizing is practically impossible.

What can be anonymized?

We’re currently supporting four object types: faces, license plate, bodies and vehicles. Additionally, we’re currently working on adding support for more object types. Any particular need? Contact our sales team!