Cargando…

Deep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection

This research is aimed to detect defects on the surface of the fabric and deep learning model optimization. Since defect detection cannot effectively solve the fabric with complex background by image processing, this research uses deep learning to identify defects. However, the current network archi...

Descripción completa

Detalles Bibliográficos
Autores principales: Ho, Chao-Ching, Chou, Wei-Chi, Su, Eugene
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8587924/
https://www.ncbi.nlm.nih.gov/pubmed/34770380
http://dx.doi.org/10.3390/s21217074
_version_ 1784598298243366912
author Ho, Chao-Ching
Chou, Wei-Chi
Su, Eugene
author_facet Ho, Chao-Ching
Chou, Wei-Chi
Su, Eugene
author_sort Ho, Chao-Ching
collection PubMed
description This research is aimed to detect defects on the surface of the fabric and deep learning model optimization. Since defect detection cannot effectively solve the fabric with complex background by image processing, this research uses deep learning to identify defects. However, the current network architecture mainly focuses on natural images rather than the defect detection. As a result, the network architecture used for defect detection has more redundant neurons, which reduces the inference speed. In order to solve the above problems, we propose network pruning with the Bayesian optimization algorithm to automatically tune the network pruning parameters, and then retrain the network after pruning. The training and detection process uses the above-mentioned pruning network to predict the defect feature map, and then uses the image processing flow proposed in this research for the final judgment during fabric defect detection. The proposed method is verified in the two self-made datasets and the two public datasets. In the part of the proposed network optimization results, the Intersection over Union (IoU) of four datasets are dropped by 1.26%, 1.13%, 1.21%, and 2.15% compared to the original network model, but the inference time is reduced to 20.84%, 40.52%, 23.02%, and 23.33% of the original network model using Geforce 2080 Ti. Furthermore, the inference time is also reduced to 17.56%, 37.03%, 19.67%, and 22.26% using the embedded system AGX Xavier. After the image processing part, the accuracy of the four datasets can reach 92.75%, 94.87%, 95.6%, and 81.82%, respectively. In this research, Yolov4 is also trained with fabric defects, and the results showed this model are not conducive to detecting long and narrow fabric defects.
format Online
Article
Text
id pubmed-8587924
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-85879242021-11-13 Deep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection Ho, Chao-Ching Chou, Wei-Chi Su, Eugene Sensors (Basel) Article This research is aimed to detect defects on the surface of the fabric and deep learning model optimization. Since defect detection cannot effectively solve the fabric with complex background by image processing, this research uses deep learning to identify defects. However, the current network architecture mainly focuses on natural images rather than the defect detection. As a result, the network architecture used for defect detection has more redundant neurons, which reduces the inference speed. In order to solve the above problems, we propose network pruning with the Bayesian optimization algorithm to automatically tune the network pruning parameters, and then retrain the network after pruning. The training and detection process uses the above-mentioned pruning network to predict the defect feature map, and then uses the image processing flow proposed in this research for the final judgment during fabric defect detection. The proposed method is verified in the two self-made datasets and the two public datasets. In the part of the proposed network optimization results, the Intersection over Union (IoU) of four datasets are dropped by 1.26%, 1.13%, 1.21%, and 2.15% compared to the original network model, but the inference time is reduced to 20.84%, 40.52%, 23.02%, and 23.33% of the original network model using Geforce 2080 Ti. Furthermore, the inference time is also reduced to 17.56%, 37.03%, 19.67%, and 22.26% using the embedded system AGX Xavier. After the image processing part, the accuracy of the four datasets can reach 92.75%, 94.87%, 95.6%, and 81.82%, respectively. In this research, Yolov4 is also trained with fabric defects, and the results showed this model are not conducive to detecting long and narrow fabric defects. MDPI 2021-10-25 /pmc/articles/PMC8587924/ /pubmed/34770380 http://dx.doi.org/10.3390/s21217074 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ho, Chao-Ching
Chou, Wei-Chi
Su, Eugene
Deep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection
title Deep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection
title_full Deep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection
title_fullStr Deep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection
title_full_unstemmed Deep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection
title_short Deep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection
title_sort deep convolutional neural network optimization for defect detection in fabric inspection
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8587924/
https://www.ncbi.nlm.nih.gov/pubmed/34770380
http://dx.doi.org/10.3390/s21217074
work_keys_str_mv AT hochaoching deepconvolutionalneuralnetworkoptimizationfordefectdetectioninfabricinspection
AT chouweichi deepconvolutionalneuralnetworkoptimizationfordefectdetectioninfabricinspection
AT sueugene deepconvolutionalneuralnetworkoptimizationfordefectdetectioninfabricinspection