Maqola

Comparative Analysis Of Convolutional Neural Networks (Cnn), Support Vector Machine (Svm) And Random Forest Algorithms For Detecting Knitted Fabric Defects

Sherzod KorabayevNamangan State Technical University , UzbekistanXusanxon BobojanovNamangan State Technical University , UzbekistanJahongir SoloxiddinovNamangan State Technical University , UzbekistanSherzod DjuraevNamangan State Technical University , Uzbekistan

American Journal Of Applied Science And Technologyjournal2025

ABI

Annotatsiya

This research presents a comparative analysis of Convolutional Neural Networks (CNN), Support Vector Machine (SVM), and Random Forest algorithms for defect detection in knitted fabrics. Experimental results on a dataset of 5000 images demonstrate that the CNN model achieved 96.8% accuracy, SVM 89.3%, and Random Forest 91.2%. The study indicates that CNN is preferable for scenarios requiring high precision, while Random Forest is more suitable with limited computational resources. These findings have practical implications for designing automated quality control systems in the knitting industry.

Mavzular

Textile materials and evaluations Industrial Vision Systems and Defect Detection Dyeing and Modifying Textile Fibers

Identifikatorlar

DOI: 10.37547/ajast/volume05issue10-19

Iqtiboslar va manbalar

0 ta iqtibos0 ta foydalanilgan manba

Koʻrsatkichlar — AkademScholar · Tez orada