Investigating the use of GANs for defect detection in industrial inspection

Student research project/Master thesis Start: now The optical inspection of components in industry is crucial to ensure the high quality of the components produced. One possibility to automate the inspection is the use of camera systems in combination with machine learning algorithms. These usually require a large number of images, especially of defective components, for learning. The acquisition of these images is not always possible, and often not economically viable. Therefore, in this thesis, a possibility to identify defective components without the need for images of defective components shall be investigated. A promising approach that will be used in this work is anomaly detection through the use of Generative Adversarial Networks (GANs).


Your subtasks

  • Literature research on Unsupervised Anomaly Detection in industrial inspection
  • Construction of a training data set based on a real component
  • Selection and training of GANs for anomaly detection
  • Evaluation of the results

Your profile

  • You are studying mechatronics, electrical engineering, mechanical engineering, computer science engineering or a comparable subject
  • You have an interest in AI topics
  • Ideally, you have programming skills (Python, etc.)
  • You have a high degree of initiative and are inquisitive

If you are interested, please contact: Ole Schmedemann |

Leave a Reply

Your email address will not be published. Required fields are marked *