A study on the automatic construction of fit-adapted models for fully fashioned flat knitted protective head masks based on bisenet facial semantic segmentation
AUTEX Research Journal · 23.01.2026 · 26 (1)
DOI: 10.1515/aut-2025-0077 ↗Kurz gefasst
Fachartikel in der Zeitschrift AUTEX Research Journal, online erschienen am 09.07.2026. Verfasst von Xuan Luo und 2 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study focuses on the issue of fit adaptation in fully fashioned flat knitted protective head masks. To address the limitations of existing products, which predominantly rely upon standardized sizing and inadequately conform to individual craniofacial morphology, an automated modeling method based on a digital head model is proposed. Utilizing a dataset constructed from CelebAMask-HQ, a bilateral segmentation network (BiSeNet) was trained to achieve precise facial semantic segmentation and feature point extraction. This process enables the automatic generation of process parameters suitable for fully fashioned flat knitting. Based on these parameters, the head mask is fabricated through the integration of frontal and lateral knitting processes, followed by dimensional validation and fit evaluation. Experimental results demonstrate that the structural and dimensional parameters generated by the proposed method exhibit high accuracy and reliability. The resultant fully fashioned flat knitted protective head masks exhibit superior conformity and comfort during wear, validating the model’s effectiveness in practical applications. This research establishes a viable technological pathway for fit-adapted construction of fully fashioned flat knitted protective head masks and contributes to the advancement of intelligent knitting technology and digital apparel engineering.
Zitieren
APA
Luo, X., Shen, B., & Li, D. (2026). A study on the automatic construction of fit-adapted models for fully fashioned flat knitted protective head masks based on bisenet facial semantic segmentation. AUTEX Research Journal, 26(1). https://doi.org/10.1515/aut-2025-0077
Vancouver
Luo X, Shen B, Li D. A study on the automatic construction of fit-adapted models for fully fashioned flat knitted protective head masks based on bisenet facial semantic segmentation. AUTEX Research Journal. 2026;26(1). doi:10.1515/aut-2025-0077
BibTeX
@article{Luo2026,
author = {Luo, Xuan and Shen, Binzi and Li, Duan},
title = {A study on the automatic construction of fit-adapted models for fully fashioned flat knitted protective head masks based on bisenet facial semantic segmentation},
journal = {AUTEX Research Journal},
year = {2026},
volume = {26},
number = {1},
doi = {10.1515/aut-2025-0077}
}
EUVIMED