Enhanced Deep Stacked CapsNet Ensemble Gazelle Neural Network for multi-level fabric defect classification

IF 2.2 4区 工程技术 Q3 CHEMISTRY, APPLIED
Hattarki Pooja, Shridevi Soma
{"title":"Enhanced Deep Stacked CapsNet Ensemble Gazelle Neural Network for multi-level fabric defect classification","authors":"Hattarki Pooja,&nbsp;Shridevi Soma","doi":"10.1111/cote.12805","DOIUrl":null,"url":null,"abstract":"<p>Fabric detection in the materials industry plays a vital role in the global economy, making effective quality control measures essential to ensure product value and reduce manufacturing waste. With the rise of Industry 4.0, manufacturing companies have been striving to develop automated fabric defect detection systems to overcome the limitations of traditional manual inspection. However, because of challenges in creating highly effective fabric defect detection methods with strong noise resistance, conventional systems often struggle to capture intricate fabric details and accurately distinguish between defect types. To address these challenges, this research introduces an innovative approach called the Enhanced Deep Stacked capsNet Ensemble Gazelle Neural Network (EDSEGNN) for multi-level local and global defect classification. By incorporating the Window-aware Guided Image Filtering technique, image quality and resolution are enhanced, enabling the detection of fine fabric details. Additionally, the Wavelet Packet Transform aids in segmenting fabric defects by identifying small patterns through varying frequency waves. In the final stage, the EDSEGNN model performs local defect identification and multi-level global defect classification, distinguishing between normal and defective patterns while categorising defect types like discoloration, stains, foreign objects, cuts, holes, thread issues and metal contamination. The proposed method achieves impressive results, with a peak accuracy of 99.8%, along with high recall (99.5%) and F1-score (99%), compared with existing methods. The proposed approach offers a highly accurate and robust solution to the challenges faced by traditional fabric defect detection systems, representing a valuable advance in automated quality control for the materials industry.</p>","PeriodicalId":10502,"journal":{"name":"Coloration Technology","volume":"141 5","pages":"711-730"},"PeriodicalIF":2.2000,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Coloration Technology","FirstCategoryId":"88","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/cote.12805","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, APPLIED","Score":null,"Total":0}
引用次数: 0

Abstract

Fabric detection in the materials industry plays a vital role in the global economy, making effective quality control measures essential to ensure product value and reduce manufacturing waste. With the rise of Industry 4.0, manufacturing companies have been striving to develop automated fabric defect detection systems to overcome the limitations of traditional manual inspection. However, because of challenges in creating highly effective fabric defect detection methods with strong noise resistance, conventional systems often struggle to capture intricate fabric details and accurately distinguish between defect types. To address these challenges, this research introduces an innovative approach called the Enhanced Deep Stacked capsNet Ensemble Gazelle Neural Network (EDSEGNN) for multi-level local and global defect classification. By incorporating the Window-aware Guided Image Filtering technique, image quality and resolution are enhanced, enabling the detection of fine fabric details. Additionally, the Wavelet Packet Transform aids in segmenting fabric defects by identifying small patterns through varying frequency waves. In the final stage, the EDSEGNN model performs local defect identification and multi-level global defect classification, distinguishing between normal and defective patterns while categorising defect types like discoloration, stains, foreign objects, cuts, holes, thread issues and metal contamination. The proposed method achieves impressive results, with a peak accuracy of 99.8%, along with high recall (99.5%) and F1-score (99%), compared with existing methods. The proposed approach offers a highly accurate and robust solution to the challenges faced by traditional fabric defect detection systems, representing a valuable advance in automated quality control for the materials industry.

增强的深度堆叠CapsNet集成瞪羚神经网络多层次织物缺陷分类
材料工业中的织物检测在全球经济中起着至关重要的作用,有效的质量控制措施对于确保产品价值和减少制造浪费至关重要。随着工业4.0的兴起,制造企业一直在努力开发自动化织物缺陷检测系统,以克服传统人工检测的局限性。然而,由于在创建具有强抗噪性的高效织物缺陷检测方法方面存在挑战,传统系统通常难以捕获复杂的织物细节并准确区分缺陷类型。为了应对这些挑战,本研究引入了一种称为增强型深度堆叠capsNet集成瞪羚神经网络(EDSEGNN)的创新方法,用于多级局部和全局缺陷分类。通过结合窗口感知引导图像滤波技术,增强了图像质量和分辨率,使精细织物细节的检测成为可能。此外,小波包变换通过不同频率的波来识别小图案,有助于分割织物缺陷。在最后阶段,EDSEGNN模型执行局部缺陷识别和多级全局缺陷分类,区分正常和缺陷模式,同时对缺陷类型进行分类,如变色、污渍、异物、切割、孔、螺纹问题和金属污染。与现有方法相比,该方法取得了令人印象深刻的结果,峰值准确率达到99.8%,召回率(99.5%)和f1分数(99%)都很高。提出的方法为传统织物缺陷检测系统面临的挑战提供了高度精确和强大的解决方案,代表了材料行业自动化质量控制的有价值的进步。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Coloration Technology
Coloration Technology 工程技术-材料科学:纺织
CiteScore
3.60
自引率
11.10%
发文量
67
审稿时长
4 months
期刊介绍: The primary mission of Coloration Technology is to promote innovation and fundamental understanding in the science and technology of coloured materials by providing a medium for communication of peer-reviewed research papers of the highest quality. It is internationally recognised as a vehicle for the publication of theoretical and technological papers on the subjects allied to all aspects of coloration. Regular sections in the journal include reviews, original research and reports, feature articles, short communications and book reviews.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信