当前位置: X-MOL 学术J. Text. Inst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Individual yarn fibre extraction from micro-CT: multilevel machine learning approach
The Journal of The Textile Institute ( IF 1.7 ) Pub Date : 2021-01-04 , DOI: 10.1080/00405000.2020.1865503
Petr Henyš 1 , Lukáš Čapek 1
Affiliation  

Abstract

The internal structure and mechanics of the fibre materials, such as yarn or woven textile, are highly complex. Exploring the fibre structure is an essential step in material engineering either from the experimental or computational point of view. In this study, a new method to extract geometrical and morphological parameters of fibre structures is proposed. The method benefits from standard image analysis and machine learning technique to efficiently extract fibre segments from microcomputer tomography data. The proposed algorithm is tested on the yarn and woven textile materials with different resolution and quality. The developed method can extract the individual fibres with varying accuracy from 73% to 100% with processing time 2–5 s on the tested samples.



中文翻译:

从微 CT 中提取单根纱线纤维:多级机器学习方法

摘要

纱线或机织纺织品等纤维材料的内部结构和力学非常复杂。从实验或计算的角度来看,探索纤维结构是材料工程中必不可少的一步。在这项研究中,提出了一种提取纤维结构几何和形态参数的新方法。该方法受益于标准图像分析和机器学习技术,可有效地从微计算机断层扫描数据中提取纤维段。所提出的算法在不同分辨率和质量的纱线和机织纺织材料上进行了测试。所开发的方法可以以 73% 到 100% 的不同精度提取单个纤维,处理时间为 2-5 秒。

更新日期:2021-01-04
down
wechat
bug