Dr Matej Ulicny is currently a senior postdoctoral researcher at the I-Form Research Centre, based in Maynooth University. He is working on image anomaly detection in Additive Manufacturing. He received his PhD in Computer Science from Trinity College Dublin Ireland, his Master’s degree in Computer Science from Halmstad University in Sweden and undergraduate degree in Applied Informatics from Comenius University in Slovakia. He has worked as a postdoctoral researcher at Trinity College Dublin and as a research engineer at the Centre for Applied Intelligent Systems Research, Halmstad University, Sweden.
Research Interests (Lay Summary)
Dr Ulicny’s research interests include Computer Vision and Machine Learning. His former research projects were centered around the feature extraction process in Machine Learning models that are commonly used for image processing tasks. In his current research, he is focused on analysing image data captured during manufacturing processes using computer vision methodologies. The goal is to detect anomalies in order to improve the manufacturing process and quality of the final product.
Technical Summary
Computer vision techniques have been successfully applied in numerous real-world problems. Convolutional Neural Networks (CNNs) and Vision Transformers are essential backbones of most of the current image processing pipelines. These pipelines have been successful in use cases such as material crack detection. We aim to design a pipeline that can be used to find anomalies in material structure from images captured during the 3D printing process. We aim to use high-resolution images to detect defects of arbitrary sizes and shapes. The focus is pointed specifically at those defects that can hamper the quality of the product. If the quality is inspected on a per-layer basis, the faulty component can be discovered and possibly corrected even before the printing process is completed.
Expertise
Artificial Intelligence, Data Analytics, Image Processing, Predictive Modeling