Open AccessStyle Transfer Using Whitening and Coloring to Realize Feature Transformation
Author(s) -
Sijia Li,
Wenbai Chen
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1654/1/012069
Subject(s) - generalization , computer science , artificial intelligence , style (visual arts) , task (project management) , process (computing) , feature (linguistics) , transformation (genetics) , simple (philosophy) , pattern recognition (psychology) , feature extraction , computational complexity theory , algorithm , transfer (computing) , mathematics , engineering , parallel computing , mathematical analysis , linguistics , philosophy , biochemistry , chemistry , archaeology , systems engineering , epistemology , gene , history , operating system
This paper proposes a general image style transfer method based on VGG network. This method does not need to learn and pre-train any kind of style in advance. The algorithm mainly implements the style transfer task by reconstructing the automatic decoder. In the process of feature extraction, the algorithm matches the content features and style features through whitening and coloring. We conducted a series of experiments with different photographic images. The experimental results show that our method has a simple training process, low computational complexity and high computational speed and excellent generalization ability.