Using deep principal components analysis-based neural networks for fabric pilling classification

Chin Shan Yang, Cheng Jian Lin, Wen-Jong Chen

Research output: Contribution to journalArticle

Abstract

A manufacturer’s fabric first undergoes an abrasion test and manual visual inspection to grade the fabric prior to shipment to ensure that there are no defects present. Manual visual classification consumes a considerable amount of human resources. Furthermore, extended use of the eyes during visual inspection often causes occupational injuries, resulting in a decrease in the efficiency of the entire operation. In order to overcome and avoid such situations, this study proposed the use of deep principal components analysis-based neural networks (DPCANNs) for fabric pilling identification. In the proposed DPCANN, the characteristics of the hairball were automatically captured using deep principal components analysis (DPCA), and the hairball class was identified using the neural network and the support vector machine (SVM). The experimental results showed that the proposed DPCANN has an average accuracy of 99.7% at the hairball level, which is in line with the needs of the industry. The results also confirmed that the proposed hairball classification method is superior to other methods.

Original languageEnglish
Article number474
JournalElectronics (Switzerland)
Volume8
Issue number5
DOIs
Publication statusPublished - 2019 May 1

Fingerprint

Principal component analysis
Neural networks
Inspection
Abrasion
Support vector machines
Personnel
Defects
Industry

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Signal Processing
  • Hardware and Architecture
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

@article{5d710e8250be4117b6a1c868dd3b3b3b,
title = "Using deep principal components analysis-based neural networks for fabric pilling classification",
abstract = "A manufacturer’s fabric first undergoes an abrasion test and manual visual inspection to grade the fabric prior to shipment to ensure that there are no defects present. Manual visual classification consumes a considerable amount of human resources. Furthermore, extended use of the eyes during visual inspection often causes occupational injuries, resulting in a decrease in the efficiency of the entire operation. In order to overcome and avoid such situations, this study proposed the use of deep principal components analysis-based neural networks (DPCANNs) for fabric pilling identification. In the proposed DPCANN, the characteristics of the hairball were automatically captured using deep principal components analysis (DPCA), and the hairball class was identified using the neural network and the support vector machine (SVM). The experimental results showed that the proposed DPCANN has an average accuracy of 99.7{\%} at the hairball level, which is in line with the needs of the industry. The results also confirmed that the proposed hairball classification method is superior to other methods.",
author = "Yang, {Chin Shan} and Lin, {Cheng Jian} and Wen-Jong Chen",
year = "2019",
month = "5",
day = "1",
doi = "10.3390/electronics8050474",
language = "English",
volume = "8",
journal = "Electronics (Switzerland)",
issn = "2079-9292",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "5",

}

Using deep principal components analysis-based neural networks for fabric pilling classification. / Yang, Chin Shan; Lin, Cheng Jian; Chen, Wen-Jong.

In: Electronics (Switzerland), Vol. 8, No. 5, 474, 01.05.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using deep principal components analysis-based neural networks for fabric pilling classification

AU - Yang, Chin Shan

AU - Lin, Cheng Jian

AU - Chen, Wen-Jong

PY - 2019/5/1

Y1 - 2019/5/1

N2 - A manufacturer’s fabric first undergoes an abrasion test and manual visual inspection to grade the fabric prior to shipment to ensure that there are no defects present. Manual visual classification consumes a considerable amount of human resources. Furthermore, extended use of the eyes during visual inspection often causes occupational injuries, resulting in a decrease in the efficiency of the entire operation. In order to overcome and avoid such situations, this study proposed the use of deep principal components analysis-based neural networks (DPCANNs) for fabric pilling identification. In the proposed DPCANN, the characteristics of the hairball were automatically captured using deep principal components analysis (DPCA), and the hairball class was identified using the neural network and the support vector machine (SVM). The experimental results showed that the proposed DPCANN has an average accuracy of 99.7% at the hairball level, which is in line with the needs of the industry. The results also confirmed that the proposed hairball classification method is superior to other methods.

AB - A manufacturer’s fabric first undergoes an abrasion test and manual visual inspection to grade the fabric prior to shipment to ensure that there are no defects present. Manual visual classification consumes a considerable amount of human resources. Furthermore, extended use of the eyes during visual inspection often causes occupational injuries, resulting in a decrease in the efficiency of the entire operation. In order to overcome and avoid such situations, this study proposed the use of deep principal components analysis-based neural networks (DPCANNs) for fabric pilling identification. In the proposed DPCANN, the characteristics of the hairball were automatically captured using deep principal components analysis (DPCA), and the hairball class was identified using the neural network and the support vector machine (SVM). The experimental results showed that the proposed DPCANN has an average accuracy of 99.7% at the hairball level, which is in line with the needs of the industry. The results also confirmed that the proposed hairball classification method is superior to other methods.

UR - http://www.scopus.com/inward/record.url?scp=85066995275&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066995275&partnerID=8YFLogxK

U2 - 10.3390/electronics8050474

DO - 10.3390/electronics8050474

M3 - Article

AN - SCOPUS:85066995275

VL - 8

JO - Electronics (Switzerland)

JF - Electronics (Switzerland)

SN - 2079-9292

IS - 5

M1 - 474

ER -