Multi-Stream Deep Convolutional Neural Network for PET Preform Surface Defects Detection and Classification

Due to the influence of technology factors, various defects will appear in the production process of PET (Polyethylene Terephthalate) preform, and affect the PET preform quality. In order to meet the requirements of the quality inspection efficiency and accuracy for PET preform, a novel multi-stream...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Taochuan Zhang, Chunmei Duan
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	PET preform surface defect multi-stream network deep CNN wavelet transform fusion Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/a812badf342d42c1a5d6dacfc27338b7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a812badf342d42c1a5d6dacfc27338b7
record_format	dspace
spelling	oai:doaj.org-article:a812badf342d42c1a5d6dacfc27338b72021-12-02T00:00:52ZMulti-Stream Deep Convolutional Neural Network for PET Preform Surface Defects Detection and Classification2169-353610.1109/ACCESS.2021.3128357https://doaj.org/article/a812badf342d42c1a5d6dacfc27338b72021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9615154/https://doaj.org/toc/2169-3536Due to the influence of technology factors, various defects will appear in the production process of PET (Polyethylene Terephthalate) preform, and affect the PET preform quality. In order to meet the requirements of the quality inspection efficiency and accuracy for PET preform, a novel multi-stream deep CNN (Convolutional Neural Network) model is performed to effectively identify and classify PET preform surface defects for the first time in this paper. In recent years, the method based on multi-stream feature fusion has a good application prospect in defect detection. In order to solve the problem of PET preform surface defects detection and classification, we study the deep CNN structure and propose a multi-stream deep network structure, which makes full use of the rich multi-feature information from different network structures. Two different deep CNNs are respectively trained to extract features from the original image, and one of them is trained to extract feature from the corresponding gradient image. We adopt wavelet transform fusion strategy to realize feature fusion and input them into ECOC-SVM (a classified Error Correcting Output Codes model using Support Vector Machines as binary learner) model for detection and classification. Using Bayesian optimization function to optimize the hyperparameters is performed to choose the best performance configuration. Through experimental analyses, the higher detection accuracy of the proposed method is 98.5%, and it is proved that the proposed model has good convergence, accuracy, stability and generalization ability.Taochuan ZhangChunmei DuanIEEEarticlePET preformsurface defectmulti-stream networkdeep CNNwavelet transform fusionElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 156973-156986 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	PET preform surface defect multi-stream network deep CNN wavelet transform fusion Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	PET preform surface defect multi-stream network deep CNN wavelet transform fusion Electrical engineering. Electronics. Nuclear engineering TK1-9971 Taochuan Zhang Chunmei Duan Multi-Stream Deep Convolutional Neural Network for PET Preform Surface Defects Detection and Classification
description	Due to the influence of technology factors, various defects will appear in the production process of PET (Polyethylene Terephthalate) preform, and affect the PET preform quality. In order to meet the requirements of the quality inspection efficiency and accuracy for PET preform, a novel multi-stream deep CNN (Convolutional Neural Network) model is performed to effectively identify and classify PET preform surface defects for the first time in this paper. In recent years, the method based on multi-stream feature fusion has a good application prospect in defect detection. In order to solve the problem of PET preform surface defects detection and classification, we study the deep CNN structure and propose a multi-stream deep network structure, which makes full use of the rich multi-feature information from different network structures. Two different deep CNNs are respectively trained to extract features from the original image, and one of them is trained to extract feature from the corresponding gradient image. We adopt wavelet transform fusion strategy to realize feature fusion and input them into ECOC-SVM (a classified Error Correcting Output Codes model using Support Vector Machines as binary learner) model for detection and classification. Using Bayesian optimization function to optimize the hyperparameters is performed to choose the best performance configuration. Through experimental analyses, the higher detection accuracy of the proposed method is 98.5%, and it is proved that the proposed model has good convergence, accuracy, stability and generalization ability.
format	article
author	Taochuan Zhang Chunmei Duan
author_facet	Taochuan Zhang Chunmei Duan
author_sort	Taochuan Zhang
title	Multi-Stream Deep Convolutional Neural Network for PET Preform Surface Defects Detection and Classification
title_short	Multi-Stream Deep Convolutional Neural Network for PET Preform Surface Defects Detection and Classification
title_full	Multi-Stream Deep Convolutional Neural Network for PET Preform Surface Defects Detection and Classification
title_fullStr	Multi-Stream Deep Convolutional Neural Network for PET Preform Surface Defects Detection and Classification
title_full_unstemmed	Multi-Stream Deep Convolutional Neural Network for PET Preform Surface Defects Detection and Classification
title_sort	multi-stream deep convolutional neural network for pet preform surface defects detection and classification
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/a812badf342d42c1a5d6dacfc27338b7
work_keys_str_mv	AT taochuanzhang multistreamdeepconvolutionalneuralnetworkforpetpreformsurfacedefectsdetectionandclassification AT chunmeiduan multistreamdeepconvolutionalneuralnetworkforpetpreformsurfacedefectsdetectionandclassification
_version_	1718404005695062016

Multi-Stream Deep Convolutional Neural Network for PET Preform Surface Defects Detection and Classification

Ejemplares similares