Affiliation:
1. Department of Textiles, The Scottish College of Textiles, Galashiels, U.K.
Abstract
Characteristic scale pattern data from batches of two fiber types commonly found in blends are gathered using imaging techniques applied to fiber surface images captured directly from a SEM. A database of fiber information is established, and linear discriminant statistical techniques are used to investigate the integrity of the data representing each fiber type. “Unknown” fiber classification strategies based on fiber type linear demarkation functions are employed with some success.
Subject
Polymers and Plastics,Chemical Engineering (miscellaneous)
Cited by
24 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Analytical Methods for the Identification and Quantitative Determination of Wool and Fine Animal Fibers: A Review;Fibers;2023-08-02
2. Panoptic Segmentation of Animal Fibers;2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC);2022-05-16
3. Identification of Wool and Cashmere Fibers by Preparation of Hollow-like Carbon Tubes after Carbonization;Journal of Natural Fibers;2022-05-02
4. Animal Fiber Identification under the Open Set Condition;Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications;2022
5. Identifying Pristine and Processed Animal Fibers using Machine Learning;2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC);2021-05-17