<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>With the rapid upgrade of AI in today’s era, the technology of designing garments by merely taking measurements of women’s clothing through traditional pattern makers followed by hand-drawn clothing style patterns by clothing designers has become increasingly inadequate to meet people’s needs. In this paper, the study of super-resolution reconstruction technology according to deep learning improves the resolution of women’s clothing style images and helps to save production costs. The overall clothing style migration method, according to the optimization DCGAN algorithm, improves the efficiency of intelligent design of women’s clothing. It is shown that the reconstruction time of a clothing style image can be completed in only 0.26s, which is much smaller than the reconstruction time of the SRCNN convolutional neural network algorithm, which is 4.30s. The loss value of the live network is 0.79, the loss value of the classical network is 1.23, and the loss value of the optimization algorithm is 0.48. The algorithm in this paper has the smallest training loss value. Therefore, the use of deep learning technology can solve the problem of traditional women’s apparel design, relying on the designer’s experience and inspiration and generating design solutions intelligently.</p>
</abstract>

With the rapid upgrade of AI in today’s era, the technology of designing garments by merely taking measurements of women’s clothing through traditional pattern makers followed by hand-drawn clothing style patterns by clothing designers has become increasingly inadequate to meet people’s needs. In this paper, the study of super-resolution reconstruction technology according to deep learning improves the resolution of women’s clothing style images and helps to save production costs. The overall clothing style migration method, according to the optimization DCGAN algorithm, improves the efficiency of intelligent design of women’s clothing. It is shown that the reconstruction time of a clothing style image can be completed in only 0.26s, which is much smaller than the reconstruction time of the SRCNN convolutional neural network algorithm, which is 4.30s. The loss value of the live network is 0.79, the loss value of the classical network is 1.23, and the loss value of the optimization algorithm is 0.48. The algorithm in this paper has the smallest training loss value. Therefore, the use of deep learning technology can solve the problem of traditional women’s apparel design, relying on the designer’s experience and inspiration and generating design solutions intelligently.

Deep learning techniques in modern women’s smart clothing design

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Deep learning techniques in modern women\u2019s smart clothing design"}

With the rapid upgrade of AI in today’s era, the technology of designing garments by merely taking measurements of women’s clothing through traditional pattern...

Deep learning techniques in modern women’s smart clothing design

Publié en ligne: 28 avr. 2023

Pages: -

Reçu: 11 févr. 2022

Accepté: 17 juil. 2022

DOI: https://doi.org/10.2478/amns.2023.1.00065

Mots clés
Women’s clothing, Intelligent clothing design, Style migration, Convolutional neural network, Super-resolution reconstruction

© 2023 Huiming Ke et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Deep learning techniques in modern women’s smart clothing design

Publié en ligne: 28 avr. 2023

Pages: -

Reçu: 11 févr. 2022

Accepté: 17 juil. 2022

DOI: https://doi.org/10.2478/amns.2023.1.00065

Mots clésWomen’s clothing, Intelligent clothing design, Style migration, Convolutional neural network, Super-resolution reconstruction

© 2023 Huiming Ke et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Women’s clothing, Intelligent clothing design, Style migration, Convolutional neural network, Super-resolution reconstruction