Performance Evaluation of Deep Learning Architectures for Tile Defect Detection
Electrical Engineering and Energy (ELENE) · 2025
DOI: 10.64470/elene.2025.16 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electrical Engineering and Energy (ELENE), 2025. Verfasst von Ayça Demir und 1 weiteren Autor:innen.
Abstract (Originalsprache)
In this study, an artificial intelligence-based quality control system was developed for the automatic detection and classification of defects in a tile. The dataset created to reduce human-induced errors in the production process and increase inspection accuracy consists of a total of 405 images. During the model development phase, CNN, MobileNetV2, ResNet50, and EfficientNetB0 architectures were used. The performance of the models was evaluated using the 10-fold cross-validation method for an objective comparison. The experimental results show that the EfficientNetB0 architecture achieved the highest performance with an accuracy rate of 96.73%. ResNet50 achieved 95.45%, CNN achieved 94.91%, and MobileNetV2 achieved 92.36% accuracy
Zitieren
APA
Demir, A., & Örnek, H. K. (2025). Performance Evaluation of Deep Learning Architectures for Tile Defect Detection. Electrical Engineering and Energy (ELENE). https://doi.org/10.64470/elene.2025.16
Vancouver
Demir A, Örnek HK. Performance Evaluation of Deep Learning Architectures for Tile Defect Detection. Electrical Engineering and Energy (ELENE). 2025. doi:10.64470/elene.2025.16
BibTeX
@article{Demir2025,
author = {Demir, Ayça and Örnek, Humar Kahramanlı},
title = {Performance Evaluation of Deep Learning Architectures for Tile Defect Detection},
journal = {Electrical Engineering and Energy (ELENE)},
year = {2025},
doi = {10.64470/elene.2025.16}
}
EUVIMED