A comparison of anomaly detection algorithms with applications on recoater streaking in an additive manufacturing process

What is it about?

While 3D printing becomes more and more viable, some defects still occur during the printing process. We highlighted the most occuring defect and tested and compared multiple detection models. Furthermore, we introduced an improvement to an existing model. We show that state-of-the art models perform very well, but specialised detection models outperform all others with the correct preprocessing.

Featured Image