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

Guardado en:

Detalles Bibliográficos
Autores principales:	Chao-Ching Ho, Wei-Chi Chou, Eugene Su
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep convolutional neural network defect detection machine vision embedded inspection deep learning network optimization pruning parameter Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/3c446f383b9e478dbd9367daba10c873
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3c446f383b9e478dbd9367daba10c873
record_format	dspace
spelling	oai:doaj.org-article:3c446f383b9e478dbd9367daba10c8732021-11-11T19:05:31ZDeep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection10.3390/s212170741424-8220https://doaj.org/article/3c446f383b9e478dbd9367daba10c8732021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7074https://doaj.org/toc/1424-8220This 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.Chao-Ching HoWei-Chi ChouEugene SuMDPI AGarticledeep convolutional neural networkdefect detectionmachine visionembedded inspectiondeep learning network optimizationpruning parameterChemical technologyTP1-1185ENSensors, Vol 21, Iss 7074, p 7074 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep convolutional neural network defect detection machine vision embedded inspection deep learning network optimization pruning parameter Chemical technology TP1-1185
spellingShingle	deep convolutional neural network defect detection machine vision embedded inspection deep learning network optimization pruning parameter Chemical technology TP1-1185 Chao-Ching Ho Wei-Chi Chou Eugene Su Deep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection
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	article
author	Chao-Ching Ho Wei-Chi Chou Eugene Su
author_facet	Chao-Ching Ho Wei-Chi Chou Eugene Su
author_sort	Chao-Ching Ho
title	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_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_sort	deep convolutional neural network optimization for defect detection in fabric inspection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/3c446f383b9e478dbd9367daba10c873
work_keys_str_mv	AT chaochingho deepconvolutionalneuralnetworkoptimizationfordefectdetectioninfabricinspection AT weichichou deepconvolutionalneuralnetworkoptimizationfordefectdetectioninfabricinspection AT eugenesu deepconvolutionalneuralnetworkoptimizationfordefectdetectioninfabricinspection
_version_	1718431638200778752

Deep Convolutional Neural Network Optimization for Defect Detection in Fabric Inspection

Ejemplares similares