Enhancing robustness to novel visual defects through StyleGAN latent space navigation: a manufacturing use case

IF 5.9 2区 工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Journal of Intelligent Manufacturing Pub Date : 2024-05-27 DOI:10.1007/s10845-024-02415-1
Spyros Theodoropoulos, Dimitrios Dardanis, Georgios Makridis, Patrik Zajec, Jože M. Rožanec, Dimosthenis Kyriazis, Panayiotis Tsanakas
{"title":"Enhancing robustness to novel visual defects through StyleGAN latent space navigation: a manufacturing use case","authors":"Spyros Theodoropoulos, Dimitrios Dardanis, Georgios Makridis, Patrik Zajec, Jože M. Rožanec, Dimosthenis Kyriazis, Panayiotis Tsanakas","doi":"10.1007/s10845-024-02415-1","DOIUrl":null,"url":null,"abstract":"<p>Visual Quality Inspection is an integral part of the manufacturing process that is becoming increasingly automated with the advent of Industry 4.0. While very beneficial, AI-driven Computer Vision Algorithms and Deep Neural Networks face several issues that may impede their adoption in practical real-life settings such as a manufacturing shop floor. One such issue arising during an AI classifier’s continuous operation is the frequent lack of robustness to novel defects appearing for the first time. Such unanticipated inputs can pose a significant risk to cyber-physical applications as a resulting out-of-context decision could compromise the integrity of the production process. While recent Machine Learning methods can theoretically tackle this problem from different angles (e.g., open-set recognition, semi-supervised learning, intelligent data augmentation), applying them to a real-life setting with a small, imbalanced dataset and high inter-class similarity can be challenging. This paper confronts such a use case aiming at the automation of the visual quality inspection of shaver shell brand prints from the electronics industry and characterized by data scarcity and the existence of small local defects. To that end, we introduce a novel data augmentation approach based on the latent space manipulation of StyleGAN, where defect data is intentionally synthesized to simulate novel inputs that can help form a boundary of the model’s knowledge. Our approach shows promising results compared to well-established open-set recognition and semi-supervised methods applied to the same problem, while its consistent performance across classifier embeddings indicates lower coupling to the final classifier.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"33 1","pages":""},"PeriodicalIF":5.9000,"publicationDate":"2024-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Intelligent Manufacturing","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s10845-024-02415-1","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Visual Quality Inspection is an integral part of the manufacturing process that is becoming increasingly automated with the advent of Industry 4.0. While very beneficial, AI-driven Computer Vision Algorithms and Deep Neural Networks face several issues that may impede their adoption in practical real-life settings such as a manufacturing shop floor. One such issue arising during an AI classifier’s continuous operation is the frequent lack of robustness to novel defects appearing for the first time. Such unanticipated inputs can pose a significant risk to cyber-physical applications as a resulting out-of-context decision could compromise the integrity of the production process. While recent Machine Learning methods can theoretically tackle this problem from different angles (e.g., open-set recognition, semi-supervised learning, intelligent data augmentation), applying them to a real-life setting with a small, imbalanced dataset and high inter-class similarity can be challenging. This paper confronts such a use case aiming at the automation of the visual quality inspection of shaver shell brand prints from the electronics industry and characterized by data scarcity and the existence of small local defects. To that end, we introduce a novel data augmentation approach based on the latent space manipulation of StyleGAN, where defect data is intentionally synthesized to simulate novel inputs that can help form a boundary of the model’s knowledge. Our approach shows promising results compared to well-established open-set recognition and semi-supervised methods applied to the same problem, while its consistent performance across classifier embeddings indicates lower coupling to the final classifier.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
通过 StyleGAN 潜在空间导航增强对新型视觉缺陷的稳健性:制造业用例
视觉质量检测是制造过程中不可或缺的一部分,随着工业 4.0 的到来,其自动化程度也在不断提高。虽然人工智能驱动的计算机视觉算法和深度神经网络非常有益,但它们也面临着一些问题,这些问题可能会阻碍它们在制造车间等实际现实环境中的应用。人工智能分类器在持续运行过程中出现的一个问题是,对于首次出现的新缺陷经常缺乏鲁棒性。这种意料之外的输入会给网络物理应用带来巨大风险,因为由此产生的断章取义的决策可能会损害生产流程的完整性。虽然最近的机器学习方法可以从不同角度(如开放集识别、半监督学习、智能数据增强)从理论上解决这一问题,但将它们应用到数据集小、不平衡且类间相似度高的现实环境中可能具有挑战性。本文面对的就是这样一个使用案例,其目的是对电子行业的剃须刀外壳品牌印花进行自动化视觉质量检测,其特点是数据稀缺和存在小的局部缺陷。为此,我们引入了一种基于 StyleGAN 潜在空间操作的新型数据增强方法,在这种方法中,缺陷数据被有意合成,以模拟有助于形成模型知识边界的新型输入。与应用于同一问题的成熟的开放集识别和半监督方法相比,我们的方法显示出了良好的效果,而它在不同分类器嵌入中的一致表现表明,它与最终分类器的耦合度较低。
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 去求助
来源期刊
Journal of Intelligent Manufacturing
Journal of Intelligent Manufacturing 工程技术-工程:制造
CiteScore
19.30
自引率
9.60%
发文量
171
审稿时长
5.2 months
期刊介绍: The Journal of Nonlinear Engineering aims to be a platform for sharing original research results in theoretical, experimental, practical, and applied nonlinear phenomena within engineering. It serves as a forum to exchange ideas and applications of nonlinear problems across various engineering disciplines. Articles are considered for publication if they explore nonlinearities in engineering systems, offering realistic mathematical modeling, utilizing nonlinearity for new designs, stabilizing systems, understanding system behavior through nonlinearity, optimizing systems based on nonlinear interactions, and developing algorithms to harness and leverage nonlinear elements.
期刊最新文献
Industrial vision inspection using digital twins: bridging CAD models and realistic scenarios Reliability-improved machine learning model using knowledge-embedded learning approach for smart manufacturing Smart scheduling for next generation manufacturing systems: a systematic literature review An overview of traditional and advanced methods to detect part defects in additive manufacturing processes A systematic multi-layer cognitive model for intelligent machine tool
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1