Quantitative Assessment of Deep Learning and Metaheuristic Optimization Techniques in Fabric Defect Detection
Pertanika Proceedings · 2025
DOI: 10.47836/pp.1.5.006 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pertanika Proceedings, 2025. Verfasst von Suresh Kumar O G und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Advancements in fabric defect detection (FDD) are explored through the application of Deep Learning (DL) and Metaheuristic Optimization (MO) techniques in this study. As textile production becomes more automated, the need for precise and speedy defect detection systems grows. We look at contemporary works that combine different DL models with MO approaches like simulated annealing, particle swarm optimisation, and genetic algorithms. The work focusses on a complete statistical evaluation of several approaches across multiple datasets, including accuracy, precision, recall, and processing cost.
Zitieren
APA
G, S. K. O., & Avanija, J. (2025). Quantitative Assessment of Deep Learning and Metaheuristic Optimization Techniques in Fabric Defect Detection. Pertanika Proceedings. https://doi.org/10.47836/pp.1.5.006
Vancouver
G SKO, Avanija J. Quantitative Assessment of Deep Learning and Metaheuristic Optimization Techniques in Fabric Defect Detection. Pertanika Proceedings. 2025. doi:10.47836/pp.1.5.006
BibTeX
@article{G2025,
author = {G, Suresh Kumar O and Avanija, J.},
title = {Quantitative Assessment of Deep Learning and Metaheuristic Optimization Techniques in Fabric Defect Detection},
journal = {Pertanika Proceedings},
year = {2025},
doi = {10.47836/pp.1.5.006}
}
EUVIMED