A Suggestion System According to Fabric Control Time
GAZI UNIVERSITY JOURNAL OF SCIENCE, cilt.35, sa.4, ss.1333-1342, 2022 (Scopus, TRDizin)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 35 Sayı: 4
- Basım Tarihi: 2022
- Doi Numarası: 10.35378/gujs.834557
- Dergi Adı: GAZI UNIVERSITY JOURNAL OF SCIENCE
- Derginin Tarandığı İndeksler: Scopus, Academic Search Premier, Aerospace Database, Aquatic Science & Fisheries Abstracts (ASFA), Communication Abstracts, Compendex, Metadex, Civil Engineering Abstracts, TR DİZİN (ULAKBİM)
- Sayfa Sayıları: ss.1333-1342
- Anahtar Kelimeler: Fabric defect, Feature extraction, Defect recognition
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- Dokuz Eylül Üniversitesi Adresli: Evet
Özet
Automatic systems facilitate many areas of life. The combination of image processing and
machine learning has opened the door to a new world. In spite of this, most of the control is done
manually in the factories where fabrics, which are the main material of textile, are produced. The
studies to automate this control process are still insufficient. In this study, it is aimed to develop
a system with the highest performance in a short time. Different feature extraction methods
(Principal Component Analysis, Local Binary Pattern) and different classifiers (K-Nearest
Neighbor, Support Vector Machine) have been tested in terms of time and different performance
metrics. Different systems have been suggested depending on whether the fabric control is done
during or after production.