full
search.png

Search

close.png

Cancel

arrow
Volume 16, Issue 1
Style Transfer Technology of Batik Pattern Based on Deep Learning

Jing Zhang & Yan Jiang

DOI: 10.3993/jfbim02171

Journal of Fiber Bioengineering & Informatics, 16 (2023), pp. 57-67.

Published online: 2023-10

Preview Full PDF 900 9151

Cited by

google scholar semantic scholar
Export citation
  • Abstract

AI painting has recently come into public view, improving the efficiency of users' creations. At present, the research and application of popular products such as characters and landscapes are more, but the research of Miao batik patterns is lacking. Therefore, this paper studies the style transfer of batik patterns from two aspects. First, a local style transfer model of batik patterns with enhanced edges is proposed. The loss function is composed of local content loss, local style loss and Laplacian loss, and the generated images have good performance in detail texture and color space. The other is to use the existing model in the AI painting tool Stable Diffusion for style transfer of batik patterns. It performs well in running time and memory occupation, but the generated image cannot inherit the style and content images well in color and detail.

  • Keywords

Style Transfer Edge Enhancement Mask Diagram Miao Batik Pattern Stable Diffusion

  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JFBI-16-57, author = {Zhang , Jing and Jiang , Yan}, title = {Style Transfer Technology of Batik Pattern Based on Deep Learning}, journal = {Journal of Fiber Bioengineering and Informatics}, year = {2023}, volume = {16}, number = {1}, pages = {57--67}, abstract = {

AI painting has recently come into public view, improving the efficiency of users' creations. At present, the research and application of popular products such as characters and landscapes are more, but the research of Miao batik patterns is lacking. Therefore, this paper studies the style transfer of batik patterns from two aspects. First, a local style transfer model of batik patterns with enhanced edges is proposed. The loss function is composed of local content loss, local style loss and Laplacian loss, and the generated images have good performance in detail texture and color space. The other is to use the existing model in the AI painting tool Stable Diffusion for style transfer of batik patterns. It performs well in running time and memory occupation, but the generated image cannot inherit the style and content images well in color and detail.

}, issn = {2617-8699}, doi = {https://doi.org/10.3993/jfbim02171}, url = {http://global-sci.org/intro/article_detail/jfbi/22060.html} }
TY - JOUR T1 - Style Transfer Technology of Batik Pattern Based on Deep Learning AU - Zhang , Jing AU - Jiang , Yan JO - Journal of Fiber Bioengineering and Informatics VL - 1 SP - 57 EP - 67 PY - 2023 DA - 2023/10 SN - 16 DO - http://doi.org/10.3993/jfbim02171 UR - https://global-sci.org/intro/article_detail/jfbi/22060.html KW - Style Transfer KW - Edge Enhancement KW - Mask Diagram KW - Miao Batik Pattern KW - Stable Diffusion AB -

AI painting has recently come into public view, improving the efficiency of users' creations. At present, the research and application of popular products such as characters and landscapes are more, but the research of Miao batik patterns is lacking. Therefore, this paper studies the style transfer of batik patterns from two aspects. First, a local style transfer model of batik patterns with enhanced edges is proposed. The loss function is composed of local content loss, local style loss and Laplacian loss, and the generated images have good performance in detail texture and color space. The other is to use the existing model in the AI painting tool Stable Diffusion for style transfer of batik patterns. It performs well in running time and memory occupation, but the generated image cannot inherit the style and content images well in color and detail.

Jing Zhang & Yan Jiang. (2023). Style Transfer Technology of Batik Pattern Based on Deep Learning. Journal of Fiber Bioengineering and Informatics. 16 (1). 57-67. doi:10.3993/jfbim02171
Copy to clipboard
BibteX RIS TXT
The citation has been copied to your clipboard