Defect intelligent recognition of membrane product based on deep learning

Defect detection plays a crucial role in the manufacturing industry, ensuring the quality of industrial products. Despite advancements in this field, current defect detection methods face two primary challenges: (1) extracting visually similar features from the background poses difficult and (2) the...

Full description

Saved in:
Bibliographic Details
Main Authors: Maonian Wu, Ling Li, Wei Peng, Tao Wu, Jinwei Yu, Bo Zheng, Shaojun Zhu
Format: Article
Language:English
Published: SAGE Publishing 2025-08-01
Series:Measurement + Control
Online Access:https://doi.org/10.1177/00202940241268952
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850097223388364800
author Maonian Wu
Ling Li
Wei Peng
Tao Wu
Jinwei Yu
Bo Zheng
Shaojun Zhu
author_facet Maonian Wu
Ling Li
Wei Peng
Tao Wu
Jinwei Yu
Bo Zheng
Shaojun Zhu
author_sort Maonian Wu
collection DOAJ
description Defect detection plays a crucial role in the manufacturing industry, ensuring the quality of industrial products. Despite advancements in this field, current defect detection methods face two primary challenges: (1) extracting visually similar features from the background poses difficult and (2) these methods struggle to identify tiny defects in the target objects. We present a feature enhancement module called the SE-CAR, which aims to handle the identified problems effectively. This module is designed to efficiently capture tiny defects in images, prioritize defect information features, and ultimately enhance the model’s predictive performance and accuracy in defect recognition tasks. In addition, Distance-IoU Non-Maximum Suppression is employed as a substitution for the original Non-Maximum Suppression. This enhances the recognition accuracy of bounding boxes, ensuring that the model maintains high detection accuracy even after complex scenarios. Moreover, the proposed methodology exhibits broad applicability across a wide spectrum of prevalent defect detection paradigms. In empirical experiments, we employ the YOLOv7 architecture as the foundation framework, integrating the proposed methodologies for the purpose of detecting defects in the membrane. The empirical evidence demonstrates a notable improvement in the performance of detecting defects in membrane products using the SE-CAR feature enhancement module and Distance-IoU Non-Maximum Suppression algorithm. In comparison to baseline networks, an increase in mAp by 6.29%, precision by 1.63%, and recall by 8.76%.
format Article
id doaj-art-2b24c0b73b5a4ffaaf81e2c852b42563
institution DOAJ
issn 0020-2940
language English
publishDate 2025-08-01
publisher SAGE Publishing
record_format Article
series Measurement + Control
spelling doaj-art-2b24c0b73b5a4ffaaf81e2c852b425632025-08-20T02:41:02ZengSAGE PublishingMeasurement + Control0020-29402025-08-015810.1177/00202940241268952Defect intelligent recognition of membrane product based on deep learningMaonian Wu0Ling Li1Wei Peng2Tao Wu3Jinwei Yu4Bo Zheng5Shaojun Zhu6Zhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources, Huzhou University, Huzhou, ChinaZhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources, Huzhou University, Huzhou, ChinaCollege of Computer Science and Technology, Guizhou University, Guiyang, ChinaHuzhou Institute, Collaborative Innovation Center for Membrane Separation and Water Treatment of Zhejiang Province, Zhejiang University of Technology, Huzhou, ChinaHuzhou Sennuo Fluorine Material Technology Co., Ltd, Huzhou, ChinaZhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources, Huzhou University, Huzhou, ChinaZhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources, Huzhou University, Huzhou, ChinaDefect detection plays a crucial role in the manufacturing industry, ensuring the quality of industrial products. Despite advancements in this field, current defect detection methods face two primary challenges: (1) extracting visually similar features from the background poses difficult and (2) these methods struggle to identify tiny defects in the target objects. We present a feature enhancement module called the SE-CAR, which aims to handle the identified problems effectively. This module is designed to efficiently capture tiny defects in images, prioritize defect information features, and ultimately enhance the model’s predictive performance and accuracy in defect recognition tasks. In addition, Distance-IoU Non-Maximum Suppression is employed as a substitution for the original Non-Maximum Suppression. This enhances the recognition accuracy of bounding boxes, ensuring that the model maintains high detection accuracy even after complex scenarios. Moreover, the proposed methodology exhibits broad applicability across a wide spectrum of prevalent defect detection paradigms. In empirical experiments, we employ the YOLOv7 architecture as the foundation framework, integrating the proposed methodologies for the purpose of detecting defects in the membrane. The empirical evidence demonstrates a notable improvement in the performance of detecting defects in membrane products using the SE-CAR feature enhancement module and Distance-IoU Non-Maximum Suppression algorithm. In comparison to baseline networks, an increase in mAp by 6.29%, precision by 1.63%, and recall by 8.76%.https://doi.org/10.1177/00202940241268952
spellingShingle Maonian Wu
Ling Li
Wei Peng
Tao Wu
Jinwei Yu
Bo Zheng
Shaojun Zhu
Defect intelligent recognition of membrane product based on deep learning
Measurement + Control
title Defect intelligent recognition of membrane product based on deep learning
title_full Defect intelligent recognition of membrane product based on deep learning
title_fullStr Defect intelligent recognition of membrane product based on deep learning
title_full_unstemmed Defect intelligent recognition of membrane product based on deep learning
title_short Defect intelligent recognition of membrane product based on deep learning
title_sort defect intelligent recognition of membrane product based on deep learning
url https://doi.org/10.1177/00202940241268952
work_keys_str_mv AT maonianwu defectintelligentrecognitionofmembraneproductbasedondeeplearning
AT lingli defectintelligentrecognitionofmembraneproductbasedondeeplearning
AT weipeng defectintelligentrecognitionofmembraneproductbasedondeeplearning
AT taowu defectintelligentrecognitionofmembraneproductbasedondeeplearning
AT jinweiyu defectintelligentrecognitionofmembraneproductbasedondeeplearning
AT bozheng defectintelligentrecognitionofmembraneproductbasedondeeplearning
AT shaojunzhu defectintelligentrecognitionofmembraneproductbasedondeeplearning