Kai Lu, Junliang Luo, Fei Wang, Zhiwei Fan, Genyuan Du, Xiangqun Zhang, Wenke Pei
{"title":"MobileViT model-based real-time fiber identification method for cashmere and wool","authors":"Kai Lu, Junliang Luo, Fei Wang, Zhiwei Fan, Genyuan Du, Xiangqun Zhang, Wenke Pei","doi":"10.1177/15589250241233758","DOIUrl":null,"url":null,"abstract":"The physical and morphological characteristics of wool and cashmere fibers exhibit notable similarities, making distinguishing them challenging. In this study, we propose a method based on a lightweight hybrid model called MobileViT, which combines a vision transformer and convolutional neural network, for the real-time identification of fiber categories. After training on a large sample dataset, the model was validated on a test set of 61,095 fiber images belonging to six categories; it took 26.2 s to achieve a recognition accuracy of 97.19%. This paper presents the first attempt to use a hybrid model of Transformer and Convolutional Neural Network (CNN) for the recognition of fiber images. Experimental results demonstrate that the model is capable of effectively extracting features from fibers, and it outperforms pure CNN models in terms of both speed and accuracy.","PeriodicalId":15718,"journal":{"name":"Journal of Engineered Fibers and Fabrics","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Engineered Fibers and Fabrics","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1177/15589250241233758","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, TEXTILES","Score":null,"Total":0}
引用次数: 0
Abstract
The physical and morphological characteristics of wool and cashmere fibers exhibit notable similarities, making distinguishing them challenging. In this study, we propose a method based on a lightweight hybrid model called MobileViT, which combines a vision transformer and convolutional neural network, for the real-time identification of fiber categories. After training on a large sample dataset, the model was validated on a test set of 61,095 fiber images belonging to six categories; it took 26.2 s to achieve a recognition accuracy of 97.19%. This paper presents the first attempt to use a hybrid model of Transformer and Convolutional Neural Network (CNN) for the recognition of fiber images. Experimental results demonstrate that the model is capable of effectively extracting features from fibers, and it outperforms pure CNN models in terms of both speed and accuracy.
期刊介绍:
Journal of Engineered Fibers and Fabrics is a peer-reviewed, open access journal which aims to facilitate the rapid and wide dissemination of research in the engineering of textiles, clothing and fiber based structures.