Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Appearance generation for colored spun yarn fabric based on conditional image‐to‐image translation

Appearance generation for colored spun yarn fabric based on conditional image‐to‐image translation The repeated trial‐weaving and proofing process are traditionally conducted to exhibit the ever‐changing appearance of the colored spun yarn fabric knitted by different colored spun yarns. In this paper, a novel method of appearance generation for colored spun yarn fabric was proposed based on conditional image‐to‐image translation. The generated image is required to have the same color and the fabric style simultaneously as the color card and the assigned style. The common pix2pix model was modified by adding the category label to the image channel to involve the style constraint. To improve the generation performance, the U‐Net architecture was replaced by the residual block architecture. Four commonly used style fabrics and different color cards were adopted to build the image pairs for experiments. The visual inspection and category similarity were used as the evaluation metrics. Experimental results reveal that the proposed method can transfer different color cards to the designated style fabrics based on the constraints, being effective and superior for image generation of colored spun yarns. The proposed scheme can provide references for the designer by presenting the image perception, saving labor, and material resources in the proofing process. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Color Research & Application Wiley

Appearance generation for colored spun yarn fabric based on conditional image‐to‐image translation

Download PDF
12 pages

Loading next page...
 
/lp/wiley/appearance-generation-for-colored-spun-yarn-fabric-based-on-Cwuxbu1hoD
Publisher
Wiley
Copyright
© 2021 Wiley Periodicals LLC
ISSN
0361-2317
eISSN
1520-6378
DOI
10.1002/col.22771
Publisher site
See Article on Publisher Site

Abstract

The repeated trial‐weaving and proofing process are traditionally conducted to exhibit the ever‐changing appearance of the colored spun yarn fabric knitted by different colored spun yarns. In this paper, a novel method of appearance generation for colored spun yarn fabric was proposed based on conditional image‐to‐image translation. The generated image is required to have the same color and the fabric style simultaneously as the color card and the assigned style. The common pix2pix model was modified by adding the category label to the image channel to involve the style constraint. To improve the generation performance, the U‐Net architecture was replaced by the residual block architecture. Four commonly used style fabrics and different color cards were adopted to build the image pairs for experiments. The visual inspection and category similarity were used as the evaluation metrics. Experimental results reveal that the proposed method can transfer different color cards to the designated style fabrics based on the constraints, being effective and superior for image generation of colored spun yarns. The proposed scheme can provide references for the designer by presenting the image perception, saving labor, and material resources in the proofing process.

Journal

Color Research & Application – Wiley

Published: Jan 8, 2022

Keywords: appearance generation; colored spun yarn fabric; conditional pix2pix model; image‐to‐image translation

References

  • Investigation of metallic color perception using real‐world materials
    Tanaka, M; Horiuchi, T
  • Modeling color change after spinning process using feedforward neural networks
    Thevenet, L; Dupont, D; Jolly‐Desodt, AM
  • Appearance change for colored spun yarn fabric based on image color transfer
    Zhang, N; Hu, Q; Wang, L
  • Incremental learning of multi‐domain image‐to‐image translations
    Tan, DS; Lin, YX; Hua, KL
  • Image‐to‐images translation for multi‐task organ segmentation and bone suppression in chest X‐ray radiography
    Eslami, M; Tabarestani, S; Albarqouni, S; Adeli, E; Navab, N; Adjouadi, M
  • Show, attend, and translate: unsupervised image translation with self‐regularization and attention
    Yang, C; Kim, T; Wang, R; Peng, H; Kuo, CCJ
  • Decoloration of multi‐color fabricimages for fabric appearance smoothness evaluation by supervised image‐to‐image translation
    Wang, JA; Shi, KJ; Wang, L
  • A novel method for weft and warp yarn segmentation in multicolour yarn‐dyed fabric images
    Luo, L; Shen, HL; Shao, SJ; Xin, JH
  • Optimization of a spectrally tunable LED daylight simulator
    Wei, M; Yang, B; Lin, Y
  • Image quality assessment: from error visibility to structural similarity
    Zhou, W; Bovik, AC; Sheikh, HR; Simoncelli, EP
  • ImageNet large scale visual recognition challenge
    Russakovsky, O; Deng, J; Su, H
  • Attention augmented multi‐scale network for single image super‐resolution
    Xiong, C; Shi, X; Gao, Z; Wang, G
  • A survey on image data augmentation for deep learning
    Shorten, C; Khoshgoftaar, TM