beh.digital

automation by machine learning

Coming from research in autonomous driving, beh.digital offers machine learning based products and services for industrial automation and quality assessment.

Our technology learns from your experts based on (un-)supervised neural network algorithms. Thereby, we solve computer vision tasks faster and more accurate in comparison to state-of-the-art programming – thus democratizing disruptive machine learning benefits for small- and medium enterprises.”

Nicolai Behmann, Founder

Our Offer

beh.cloud

Learning from your employees and co-workers by training an artificial intelligence in the cloud. Simply upload your dataset and we will teach your cameras to think.

beh.consulting

Do you have a problem that can be solved by human vision, but no software yet? We help you out with our machine learning expertise and affinity for fast and simple solutions.

(Un-)supervised Learning

State-of-the-art machine learning algorithms are used to classify images, objects or pixels or detect anomalies from your trained, ideal world. Starting with less than 20 training samples for fair and easy problems.

Classification

Which object is shown in the image? To which class does it belong? What is the quality level?

Get a corresponding class to the given image, based on your training.

Examples: Sorting, action trigger, quality assessment

Detection

Which objects are in the frame? Where are they located? Extract a list of classified bounding boxes from the image and grab or sort the objects.

Examples: Object sorting, quality assessment, object count, object position

Segmentation

Do you need the exact surface of an element or the contour of a particular class of objects? Segmentation is your way to get pixel-wise annotations.

Examples: Automation, container filling level, object area / borde