Fabric Defect Detection Using YOLOv2 and YOLO v3 Tiny - Computational Intelligence in Data Science Access content directly
Conference Papers Year : 2020

Fabric Defect Detection Using YOLOv2 and YOLO v3 Tiny

R. Sujee
  • Function : Author
  • PersonId : 1117255
D. Shanthosh
  • Function : Author
  • PersonId : 1117256
L. Sudharsun
  • Function : Author
  • PersonId : 1117257

Abstract

The paper aims to classify the defects in a fabric material using deep learning and neural network methodologies. For this paper, 6 classes of defects are considered, namely, Rust, Grease, Hole, Slough, Oil Stain, and, Broken Filament. This paper has implemented both the YOLOv2 model and the YOLOv3 Tiny model separately using the same fabric data set which was collected for this research, which consists of six types of defects, and uses the convolutional weights which were pre-trained on Imagenet dataset. Observed and documented the success rate of both the model in detecting the defects in the fabric material.
Fichier principal
Vignette du fichier
507484_1_En_15_Chapter.pdf (417.75 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03434800 , version 1 (18-11-2021)

Licence

Attribution

Identifiers

Cite

R. Sujee, D. Shanthosh, L. Sudharsun. Fabric Defect Detection Using YOLOv2 and YOLO v3 Tiny. 3rd International Conference on Computational Intelligence in Data Science (ICCIDS), Feb 2020, Chennai, India. pp.196-204, ⟨10.1007/978-3-030-63467-4_15⟩. ⟨hal-03434800⟩
153 View
126 Download

Altmetric

Share

Gmail Facebook X LinkedIn More