Spyros Theodoropoulos

Spyros Theodoropoulos

Auto-generated profile, based on publicly available information

Spyros Theodoropoulos

National Technical University of Athens

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 February 2024 in International Journal of Production Research
Verified
Journal Article
Open access
PZPatrik Zajec
Patrik Zajec
Jože RožanecJože Rožanec
Jože Rožanec
STSpyros Theodoropoulos
Spyros Theodoropoulos
MFMihail Fontul
Mihail Fontul
EKErik Koehorst
Erik Koehorst
DMDunja_Mladenic Mladenic
Dunja_Mladenic Mladenic

17 January 2024 in Machine Learning
Verified
Journal Article
Open access
PDF file
STSpyros Theodoropoulos
Spyros Theodoropoulos
PZPatrik Zajec
Patrik Zajec
Jože RožanecJože Rožanec
Jože Rožanec
Dimosthenis KyriazisDimosthenis Kyriazis
Dimosthenis Kyriazis
PTPANAYIOTIS TSANAKAS
PANAYIOTIS TSANAKAS
Visual defect recognition and its manufacturing applications have been an upcoming topic in recent AI research. Defect datasets are often severely imbalanced and can be additionally burdened with separating classes of high visual similarity. Although various methods of data augmentation have been proposed to mitigate the class imbalance, they often fail to cope with tinier minority classes or have fidelity issues with smaller defects while, at the same time, needing significant computational resources to train. Also, augmentation based on vector-based oversampling struggles to produce high-fidelity inputs and is hard to apply on custom CNN architectures, which often perform better for this type of problem. Our work presents an image-level oversampling method based on an instance-based image generator that can be applied to any CNN directly during the training process without increasing the order of training time required. It is based on identifying a small number of the most uncertain base samples close to the estimated class boundaries and using them as seeds for augmentation. The resulting images are of high visual quality preserving small class differences, and they also improve the classifier boundary leading to higher recall scores than other state-of-the-art approaches.

27 May 2024 in Journal of Intelligent Manufacturing
Verified
Journal Article
Closed access
PDF file
STSpyros Theodoropoulos
Spyros Theodoropoulos
DDDimitrios Dardanis
Dimitrios Dardanis
GMGeorgios Makridis
Georgios Makridis
PZPatrik Zajec
Patrik Zajec
Jože RožanecJože Rožanec
Jože Rožanec
PTPANAYIOTIS TSANAKAS
PANAYIOTIS TSANAKAS

23 June 2025
Verified
Book Chapter
Closed access
PDF file
STSpyros Theodoropoulos
Spyros Theodoropoulos
GMGeorgios Makridis
Georgios Makridis
APAristodemos Pnevmatikakis
Aristodemos Pnevmatikakis
VMVrettos Moulos
Vrettos Moulos
DKDimosthenis Kyriazis
Dimosthenis Kyriazis
PTPanayiotis Tsanakas
Panayiotis Tsanakas

19 December 2022 in arXiv
Verified
Preprint
Open access
PDF file
Jože RožanecJože Rožanec
Jože Rožanec
PZPatrik Zajec
Patrik Zajec
STSpyros Theodoropoulos
Spyros Theodoropoulos
EKErik Koehorst
Erik Koehorst
BFBlaž Fortuna
Blaž Fortuna
DMDunja Mladenić
Dunja Mladenić
Quality control is a crucial activity performed by manufacturing companies to ensure their products conform to the requirements and specifications. The introduction of artificial intelligence models enables to automate the visual quality inspection, speeding up the inspection process and ensuring all products are evaluated under the same criteria. In this research, we compare supervised and unsupervised defect detection techniques and explore data augmentation techniques to mitigate the data imbalance in the context of automated visual inspection. Furthermore, we use Generative Adversarial Networks for data augmentation to enhance the classifiers' discriminative performance. Our results show that state-of-the-art unsupervised defect detection does not match the performance of supervised models but can be used to reduce the labeling workload by more than 50%. Furthermore, the best classification performance was achieved considering GAN-based data generation with AUC ROC scores equal to or higher than 0,9898, even when increasing the dataset imbalance by leaving only 25\% of the images denoting defective products. We performed the research with real-world data provided by Philips Consumer Lifestyle BV.

8 September 2024
Verified
Book Chapter
Closed access
PDF file
STSpyros Theodoropoulos
Spyros Theodoropoulos
GMGeorgios Makridis
Georgios Makridis
DKDimosthenis Kyriazis
Dimosthenis Kyriazis
PTPanayiotis Tsanakas
Panayiotis Tsanakas