Prediction of textile pilling resistance using optical coherence tomography
Abstract This paper describes a new method of textile pilling prediction, based on multivariate analysis of the spatial layer above the surface. The original idea of the method is the acquisition of 3D fabric image using optical coherence tomography (OCT) with infrared light, which allows for the fa...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-23230-9 |
| _version_ | 1811223637217247232 |
|---|---|
| author | Jarosław Gocławski Joanna Sekulska-Nalewajko Ewa Korzeniewska |
| author_facet | Jarosław Gocławski Joanna Sekulska-Nalewajko Ewa Korzeniewska |
| author_sort | Jarosław Gocławski |
| collection | DOAJ |
| description | Abstract This paper describes a new method of textile pilling prediction, based on multivariate analysis of the spatial layer above the surface. The original idea of the method is the acquisition of 3D fabric image using optical coherence tomography (OCT) with infrared light, which allows for the fabric fuzz visualization with high sensitivity. The pilling layer, reconstructed with the resolution of $$10\times 10\times 5.5 \; \upmu \mathrm {m}$$ 10 × 10 × 5.5 μ m , includes reliable textural information related to the amount of loose fibers and bunches appearing as a result of abrasion. Pilling intensity was assigned by supervised classification of the textural features using both linear (PLS-DA - partial least squares discriminant analysis, LDA - linear discriminant analysis) and non-linear (SVM - support vector machine) classifiers. The results demonstrated that the method is more suitable for fabrics after short-term abrasion, when the fuzz prevails over tangled fibers in the pilling layer. In that case, pilling grades were predicted with $$>98\%$$ > 98 % accuracy, sensitivity and specificity (for SVM model). The validation accuracy of the tested models after machine abrasion achieves lower values (up to $$90.4\%$$ 90.4 % for LDA model). With our method, we clearly showed that OCT can be used to quantitatively trace appearance changes of fabric samples due to test abrasion. |
| first_indexed | 2024-04-12T08:36:12Z |
| format | Article |
| id | doaj.art-5429106f3d65405b868b5b31565dc931 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T08:36:12Z |
| publishDate | 2022-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-5429106f3d65405b868b5b31565dc9312022-12-22T03:40:00ZengNature PortfolioScientific Reports2045-23222022-10-0112111510.1038/s41598-022-23230-9Prediction of textile pilling resistance using optical coherence tomographyJarosław Gocławski0Joanna Sekulska-Nalewajko1Ewa Korzeniewska2Institute of Applied Computer Science, Lodz University of TechnologyInstitute of Applied Computer Science, Lodz University of TechnologyInstitute of Electrical Engineering Systems, Lodz University of TechnologyAbstract This paper describes a new method of textile pilling prediction, based on multivariate analysis of the spatial layer above the surface. The original idea of the method is the acquisition of 3D fabric image using optical coherence tomography (OCT) with infrared light, which allows for the fabric fuzz visualization with high sensitivity. The pilling layer, reconstructed with the resolution of $$10\times 10\times 5.5 \; \upmu \mathrm {m}$$ 10 × 10 × 5.5 μ m , includes reliable textural information related to the amount of loose fibers and bunches appearing as a result of abrasion. Pilling intensity was assigned by supervised classification of the textural features using both linear (PLS-DA - partial least squares discriminant analysis, LDA - linear discriminant analysis) and non-linear (SVM - support vector machine) classifiers. The results demonstrated that the method is more suitable for fabrics after short-term abrasion, when the fuzz prevails over tangled fibers in the pilling layer. In that case, pilling grades were predicted with $$>98\%$$ > 98 % accuracy, sensitivity and specificity (for SVM model). The validation accuracy of the tested models after machine abrasion achieves lower values (up to $$90.4\%$$ 90.4 % for LDA model). With our method, we clearly showed that OCT can be used to quantitatively trace appearance changes of fabric samples due to test abrasion.https://doi.org/10.1038/s41598-022-23230-9 |
| spellingShingle | Jarosław Gocławski Joanna Sekulska-Nalewajko Ewa Korzeniewska Prediction of textile pilling resistance using optical coherence tomography Scientific Reports |
| title | Prediction of textile pilling resistance using optical coherence tomography |
| title_full | Prediction of textile pilling resistance using optical coherence tomography |
| title_fullStr | Prediction of textile pilling resistance using optical coherence tomography |
| title_full_unstemmed | Prediction of textile pilling resistance using optical coherence tomography |
| title_short | Prediction of textile pilling resistance using optical coherence tomography |
| title_sort | prediction of textile pilling resistance using optical coherence tomography |
| url | https://doi.org/10.1038/s41598-022-23230-9 |
| work_keys_str_mv | AT jarosławgocławski predictionoftextilepillingresistanceusingopticalcoherencetomography AT joannasekulskanalewajko predictionoftextilepillingresistanceusingopticalcoherencetomography AT ewakorzeniewska predictionoftextilepillingresistanceusingopticalcoherencetomography |