CNN方法的一种新型工业应用:圆型针织机上织物实时检测与缺陷分类

IF 0.6 4区工程技术 Q4 MATERIALS SCIENCE, TEXTILES

Tekstil Ve Konfeksiyon Pub Date : 2022-07-07 DOI:10.32710/tekstilvekonfeksiyon.1017016

H. Çelik, L. Dülger, Burak Öztaş, Mehmet Kertmen, Elif Gülteki̇n

{"title":"CNN方法的一种新型工业应用:圆型针织机上织物实时检测与缺陷分类","authors":"H. Çelik, L. Dülger, Burak Öztaş, Mehmet Kertmen, Elif Gülteki̇n","doi":"10.32710/tekstilvekonfeksiyon.1017016","DOIUrl":null,"url":null,"abstract":"Fabric Automatic Visual Inspection (FAVI) system provides reliable performance on fabric defects inspection. This study presents a machine vision system developed to adapt in circular knitting machines where fabric defects can be automatically controlled and detected defects can be classified. The knitted fabric surface are detected during real-time manufacturing. For the classification process, three different transfer learning architectures (ResNet-50, AlexNet, GoogLeNet) have been applied. The five common knitted fabric defects were recognized with the artificial intelligence-based software and classified with an average success rate of 98% using ResNet-50 architecture. The success rates of the trained networks were compared.","PeriodicalId":22221,"journal":{"name":"Tekstil Ve Konfeksiyon","volume":"1 1","pages":""},"PeriodicalIF":0.6000,"publicationDate":"2022-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Novel Industrial Application of CNN Approach: Real Time Fabric Inspection and Defect Classification on Circular Knitting Machine\",\"authors\":\"H. Çelik, L. Dülger, Burak Öztaş, Mehmet Kertmen, Elif Gülteki̇n\",\"doi\":\"10.32710/tekstilvekonfeksiyon.1017016\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Fabric Automatic Visual Inspection (FAVI) system provides reliable performance on fabric defects inspection. This study presents a machine vision system developed to adapt in circular knitting machines where fabric defects can be automatically controlled and detected defects can be classified. The knitted fabric surface are detected during real-time manufacturing. For the classification process, three different transfer learning architectures (ResNet-50, AlexNet, GoogLeNet) have been applied. The five common knitted fabric defects were recognized with the artificial intelligence-based software and classified with an average success rate of 98% using ResNet-50 architecture. The success rates of the trained networks were compared.\",\"PeriodicalId\":22221,\"journal\":{\"name\":\"Tekstil Ve Konfeksiyon\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":0.6000,\"publicationDate\":\"2022-07-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Tekstil Ve Konfeksiyon\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.32710/tekstilvekonfeksiyon.1017016\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"MATERIALS SCIENCE, TEXTILES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tekstil Ve Konfeksiyon","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.32710/tekstilvekonfeksiyon.1017016","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"MATERIALS SCIENCE, TEXTILES","Score":null,"Total":0}

引用次数: 0

摘要

织物自动视觉检测系统(FAVI)为织物疵点检测提供了可靠的性能。本文提出了一种适用于圆型针织机的机器视觉系统，该系统可以自动控制织物疵点并对检测到的疵点进行分类。在生产过程中对针织物表面进行实时检测。对于分类过程，应用了三种不同的迁移学习架构(ResNet-50, AlexNet, GoogLeNet)。采用基于人工智能的软件对五种常见的针织物缺陷进行识别，并采用ResNet-50架构进行分类，平均成功率为98%。比较了训练后网络的成功率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A Novel Industrial Application of CNN Approach: Real Time Fabric Inspection and Defect Classification on Circular Knitting Machine

Fabric Automatic Visual Inspection (FAVI) system provides reliable performance on fabric defects inspection. This study presents a machine vision system developed to adapt in circular knitting machines where fabric defects can be automatically controlled and detected defects can be classified. The knitted fabric surface are detected during real-time manufacturing. For the classification process, three different transfer learning architectures (ResNet-50, AlexNet, GoogLeNet) have been applied. The five common knitted fabric defects were recognized with the artificial intelligence-based software and classified with an average success rate of 98% using ResNet-50 architecture. The success rates of the trained networks were compared.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Tekstil Ve Konfeksiyon 工程技术-材料科学：纺织

CiteScore

1.40

自引率

33.30%

发文量

审稿时长

>12 weeks

期刊介绍： Tekstil ve Konfeksiyon, publishes papers on both fundamental and applied research in various branches of apparel and textile technology and allied areas such as production and properties of natural and synthetic fibers, yarns and fabrics, technical textiles, finishing applications, garment technology, analysis, testing, and quality control.