Aarhus University Seal

Exploring AI's Frontiers: Accuracy in Anomaly Detection for Irregular Textures Through High-Performance Computer Vision Techniques

PhD defence, Wednesday 28 February 2024, Mehdi Rafiei Foroushani

Mehdi Rafiei Foroushani

In the context of technological advancements in intelligent industrial production, this thesis tackles vital challenges in harnessing Artificial Intelligence (AI) for irregular texture products. Throughout his doctoral studies, Mehdi Rafiei introduced innovative deep computer vision models aimed at discerning abnormalities and refining anomaly localization within irregular textures. The proposed methods effectively addressed the challenges arising from the inherent randomness in irregular products and their potential defects.

By delving into the intricacies of irregular texture products, this thesis demonstrated that meticulously crafted AI methodologies, extending their high capability beyond regular objects, can contribute significantly to the potential application of computer vision in anomaly detection and localization for irregular textures.

The PhD study was completed at the Department of Electrical and Computer Engineering, Faculty of Technical Sciences, Aarhus University.

This summary was prepared by the PhD student.

Time: Wednesday 28 February 2024 at 13.00
Place: Building 5125 (Edison), room 424, Electrical and Computer Engineering, Aarhus University, Finlandsgade 22, 8200 Aarhus N
Title of PhD thesis: Advancing Computer Vision in Irregular Texture Product Analysis
Contact information: Mehdi Rafiei, e-mail: rafiei@ece.au.dk, tel.: +45 28992075.

Members of the assessment committee:
Professor Murat Kulahci, Department of Applied Mathematics and Computer Science, Technical University of Denmark (DTU), Denmark

Associate Professor Ilkka Pölönen, Faculty of Information Technology, University of Jyväskylä, Finland

Associate Professor Qi Zhang (chair), Department of Electrical and Computer Engineering, Aarhus University, Denmark

Main supervisor:
Professor Alexandros Iosifidis, Department of Electrical and Computer Engineering, Aarhus University, Denmark

Language: The PhD dissertation will be defended in English

The defence is public.
The PhD thesis is available for reading at the Graduate School of Technical Sciences/GSTS, Jens Baggesens Vej 53, building 5221, 8200 Aarhus N.

 

17427 / i43