Title
Impressions2Font: Generating Fonts by Specifying Impressions
Abstract
Various fonts give us various impressions, which are often represented by words. This paper proposes Impressions2Font (Imp2Font) that generates font images with specific impressions. Imp2Font is an extended version of conditional generative adversarial networks (GANs). More precisely, Imp2Font accepts an arbitrary number of impression words as the condition to generate the font images. These impression words are converted into a soft-constraint vector by an impression embedding module built on a word embedding technique. Qualitative and quantitative evaluations prove that Imp2Font generates font images with higher quality than comparative methods by providing multiple impression words or even unlearned words.
Year
DOI
Venue
2021
10.1007/978-3-030-86334-0_48
DOCUMENT ANALYSIS AND RECOGNITION, ICDAR 2021, PT III
Keywords
DocType
Volume
Font impression, Conditional GAN, Impression embedding
Conference
12823
ISSN
Citations 
PageRank 
0302-9743
0
0.34
References 
Authors
0
3
Name
Order
Citations
PageRank
Seiya Matsuda100.68
Akisato Kimura224428.03
Seiichi Uchida3790105.59