Intelligent Creative Design of Textile Patterns Based on Convolutional Neural Network

  • Wang YingEmail author
  • Liu Zhengdong
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 885)


Deep learning technology has been developing significantly in the field of pattern recognition in recent years. As an important research achievement by theorized principles of human brain function, multi-layer artificial neural network has achieved impressive results in visual processing. In particular, deep dream (DD) is algorithm, based on deep-learning convolutional neural network (CNN), that blends visual qualities from multiple source images to create a new output image and provides a new opportunity for the design of textile patterns. This paper first introduces the CNN model. A model of textile design aided design based on DD is proposed. And based on the depth learning framework Tensorflow and Torch, using the deep neural network GoogleNet and ResNet, realizes the intelligent aided design system of textile pattern based on convolutional neural network.


Convolutional neural network (CNN) Deep dream Textile pattern 



This work was funded by Beijing Science and Technology Program (Z171100005017004).


  1. 1.
    Keshavan, M.S., Sudarshan, M.: Deep dreaming, aberrant salience and psychosis: connecting the dots by artificial neural networks. Schizophr. Res. 188, 178–181 (2017)CrossRefGoogle Scholar
  2. 2.
    Mordvintsev, A., Olah, C., Tyka, M.: Inceptionism: going deeper into neural networks.
  3. 3.
    McCaig, G., DiPaola, S., Gabora, L.: Deep convolutional networks as models of generalization and blending within visual creativity. In: Proceedings of the Seventh International Conference on Computational Creativity, pp. 156–163 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Basic Teaching DepartmentBeijing Institute of Fashion TechnologyBeijingChina
  2. 2.School of FashionBeijing Institute of Fashion TechnologyBeijingChina

Personalised recommendations