Research on Surface Defects Classification for PET Preform by Fusing Multi-Scale Features

Product quality control is an important component of PET preform production process. In order to improve the accuracy and reliability of PET preform detection, reduce the cost of product quality defects, and improve the overall level of product quality, this paper proposes a surface defect detection...

Full description

Saved in:
Bibliographic Details
Main Authors: Chunmei Duan, Taochuan Zhang, Lei Han, Huilin Tan
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11082268/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849687457687142400
author Chunmei Duan
Taochuan Zhang
Lei Han
Huilin Tan
author_facet Chunmei Duan
Taochuan Zhang
Lei Han
Huilin Tan
author_sort Chunmei Duan
collection DOAJ
description Product quality control is an important component of PET preform production process. In order to improve the accuracy and reliability of PET preform detection, reduce the cost of product quality defects, and improve the overall level of product quality, this paper proposes a surface defect detection method for PET preform based on multi-scale feature fusion. Multi-scale features fusion combines features from different scales to produce more accurate and robust feature representations, which improve the accuracy, stability and adaptability of PET preform detection model. This feature processing model constructs a three-branch network, generating feature maps of different sizes. Then, the low-level feature, the middle-level feature and the high-level feature are fused to obtain a PET preform feature map based on multi-scale feature fusion by using a maximum value fusion strategy. The original image and feature map of the PET preform are respectively input into the deep convolutional neural network for feature extraction and fusion. And finally the fusion features are input into the ECOC-SVM to achieve surface defect classification of the PET preform. The machine vision platform is designed for collecting and detecting PET preform data. By importing the model designed in this paper, surface defect recognition and defect category judgment of PET preform can be achieved. Through experimental data analysis, the higher testing detection accuracy of this method is 98.8%, with an average testing accuracy of 97.1%.
format Article
id doaj-art-77e76707b15b43bea7fb82f90faf1a2e
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-77e76707b15b43bea7fb82f90faf1a2e2025-08-20T03:22:19ZengIEEEIEEE Access2169-35362025-01-011313431213432410.1109/ACCESS.2025.358955911082268Research on Surface Defects Classification for PET Preform by Fusing Multi-Scale FeaturesChunmei Duan0https://orcid.org/0000-0002-0924-3784Taochuan Zhang1https://orcid.org/0000-0002-0489-8562Lei Han2https://orcid.org/0009-0007-7023-3693Huilin Tan3https://orcid.org/0009-0006-2524-5719School of Mechanical Engineering, Guangdong Ocean University, Zhanjiang, ChinaSchool of Mechanical Engineering, Guangdong Ocean University, Zhanjiang, ChinaSchool of Automobile and Transportation Engineering, Guangdong Polytechnic Normal University, Guangzhou, ChinaCollege of Information Science and Engineering, Shaoyang University, Shaoyang, ChinaProduct quality control is an important component of PET preform production process. In order to improve the accuracy and reliability of PET preform detection, reduce the cost of product quality defects, and improve the overall level of product quality, this paper proposes a surface defect detection method for PET preform based on multi-scale feature fusion. Multi-scale features fusion combines features from different scales to produce more accurate and robust feature representations, which improve the accuracy, stability and adaptability of PET preform detection model. This feature processing model constructs a three-branch network, generating feature maps of different sizes. Then, the low-level feature, the middle-level feature and the high-level feature are fused to obtain a PET preform feature map based on multi-scale feature fusion by using a maximum value fusion strategy. The original image and feature map of the PET preform are respectively input into the deep convolutional neural network for feature extraction and fusion. And finally the fusion features are input into the ECOC-SVM to achieve surface defect classification of the PET preform. The machine vision platform is designed for collecting and detecting PET preform data. By importing the model designed in this paper, surface defect recognition and defect category judgment of PET preform can be achieved. Through experimental data analysis, the higher testing detection accuracy of this method is 98.8%, with an average testing accuracy of 97.1%.https://ieeexplore.ieee.org/document/11082268/PET preformmulti-scale featuresfeatures fusionECOC-SVMdetection and classification
spellingShingle Chunmei Duan
Taochuan Zhang
Lei Han
Huilin Tan
Research on Surface Defects Classification for PET Preform by Fusing Multi-Scale Features
IEEE Access
PET preform
multi-scale features
features fusion
ECOC-SVM
detection and classification
title Research on Surface Defects Classification for PET Preform by Fusing Multi-Scale Features
title_full Research on Surface Defects Classification for PET Preform by Fusing Multi-Scale Features
title_fullStr Research on Surface Defects Classification for PET Preform by Fusing Multi-Scale Features
title_full_unstemmed Research on Surface Defects Classification for PET Preform by Fusing Multi-Scale Features
title_short Research on Surface Defects Classification for PET Preform by Fusing Multi-Scale Features
title_sort research on surface defects classification for pet preform by fusing multi scale features
topic PET preform
multi-scale features
features fusion
ECOC-SVM
detection and classification
url https://ieeexplore.ieee.org/document/11082268/
work_keys_str_mv AT chunmeiduan researchonsurfacedefectsclassificationforpetpreformbyfusingmultiscalefeatures
AT taochuanzhang researchonsurfacedefectsclassificationforpetpreformbyfusingmultiscalefeatures
AT leihan researchonsurfacedefectsclassificationforpetpreformbyfusingmultiscalefeatures
AT huilintan researchonsurfacedefectsclassificationforpetpreformbyfusingmultiscalefeatures