Int J Performability Eng ›› 2020, Vol. 16 ›› Issue (8): 1271-1278.doi: 10.23940/ijpe.20.08.p14.12711278

Previous Articles     Next Articles

Improving Font Effect Generation based on Pyramid Style Feature

Feiyu Zhanga,b, Yi Yangb, Weixing Huangb, Guigang Zhangb, and Jian Wangb,*   

  1. aSchool of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China;
    bInstitute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
  • Submitted on ; Revised on ; Accepted on
  • Contact: *E-mail address: jian.wang@ia.ac.cn
  • About author:yu Zhang is a graduate student at the University of Chinese Academy of Sciences. His research interests include style transfer and deep learning.Yi Yang is an Assistant professor at the Institute of Automation, Chinese Academy of Sciences. His research interests include data mining and visualization.Weixing Huang is an Assistant professor at the Institute of Automation, Chinese Academy of Sciences. Her research interests include literature digitization.Guigang Zhang is a Professor at the Institute of Automation, Chinese Academy of Sciences. His research interests include prognostics and health management.Jian Wang is a Professor at the Institute of Automation, Chinese Academy of Sciences. His research interests include deep learning and control theory.

Abstract: The task of font effect generation is stylizing the shape and texture of style images into font images. There exist some methods to handle this task. However, stylized font images become unrecognized when the glyph structure is quite complicated. This paper proposes a font effect generation model based on pyramid style feature. Morphology operations are utilized to improve the transferring effect. Experiments show that our proposed method is more suitable for stylizing complex glyph images than other state-of-the-arts methods.

Key words: font effect generation, pyramid feature, complex glyph