Settings for cookies and data collection

We use strictly necessary cookies on our website. They are in place to keep the session alive and save your indication on this notification for this and future sessions. You can manage and control these cookies in your browser settings.

Please decide which further cookies you want to allow:

Statistics cookies:  We use Google Analytics to analyze the access to our website and thus improve the offer. For this purpose, data on website usage is transmitted anonymously to Google.

You can find more information on the Imprint and Data Privacy Policypages, where you can change this setting later.

Computer vision for industrial defect detection

I4.0 computer vision has gone a long way since the early 2000s but discriminating OK from NOK parts on the shop-floor is still a demanding task – Read along to learn about challenges and solutions.

Semantic image segmentation

Semantic image segmentation identifies object boundaries on a per-pixel basis. One obvious application in manufacturing is the detection and size measurement of defects. Given stable imaging conditions and advanced pre- and post-processing tools a suitable neural architecture can detect minute defects also under difficult conditions – e.g.. on reflective, contaminated surfaces.
With our TensorFlow-based d-vision library we have realized cloud-based and on-premises image segmentation solutions for different customers. We use a public dataset to discuss typical challenges, workflows, and performance KPIs.