Computer Generated Algorithm of Sand Painting Based on Convolutional Neural Network

The neural style transfer of sand painting is to transform the style with the artistic image of sand painting into another image, and to create a new art image with appreciation while maintaining the semantic content of the image. This paper introduces a sand painting image simulation algorithm base...

Full description

Saved in:
Bibliographic Details
Published in2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC) Vol. 2; pp. 89 - 92
Main Authors Li, Fangfang, Sun, Dong, Zhu, De, Duan, Yunsheng, Lu, Yixiang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2019
Subjects
Convolutional neural network
Convolutional neural networks
Cybernetics
Human-machine systems
Image style transfer
Linear programming
Neural style transfer
Sand painting
Semantics
Transforms
Online AccessGet full text
DOI10.1109/IHMSC.2019.10116

Cover

More Information
Summary:The neural style transfer of sand painting is to transform the style with the artistic image of sand painting into another image, and to create a new art image with appreciation while maintaining the semantic content of the image. This paper introduces a sand painting image simulation algorithm based on convolutional neural network. The algorithm utilizes the output of the VGG16 network as an advanced feature of the image to achieve the content of the target image by separating and recombining the content features and style features of the input image. The fusion of sand painting form and high quality computer art works proves the correctness and effectiveness of the algorithm.
DOI:10.1109/IHMSC.2019.10116