The Application of Style Transfer Algorithm in Han Embroidery Design

Objective To explore the method of intelligent image generation in order to solve the problem of image style diversity in intelligent generation. In order to solve the problems of less innovation and limited automatic generation of Han embroidery pattern, this paper proposes a style transfer algorithm of Han embroidery pattern based on pre-trained convolutional neural network to realize fast and accurate transfer of Han embroidery style. Methods The patterns in Han embroidery were analyzed and the key elements were extracted. The patterns were deduced and designed by the style transfer algorithm of VGG19 network. Results Through the combination of digital style transfer algorithm and Han embroidery pattern, the innovative texture pattern of Han embroidery was quickly derived. Conclusion The combination of style transfer technology and Han embroidery pattern can promote the self-innovation of Han embroidery pattern and improve the creative efficiency of pattern design. This paper explores the application of artificial intelligence in traditional patterns, improves the artistry and richness of image utilization, and provides a new idea for the innovation of intelligent enabled images.