| Presentation | 2020-03-05 [Poster Presentation] Personalized font system Yuto Yamamoto, Michiharu Niimi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | For modern computer society, one may need human touch character font system to enjoy making communication through Internet. An approach to build such font system is to modify the usual font installed in one's computer devices. In this paper, we consider a font system that reproduces personal handwritten characters by transforming the usual fonts, and describe how to modify them into beautiful characters without losing the feeling of handwriting. Two methods are proposed: one is a method using deep neural networks based on GAN called by zi2zi and another is a method for extracting displacement information using energy functional minimization. As an example of beautiful characters, we adopted the shape of HG textbook font which is a square typeface, and realized beautiful characters by moving handwritten characters to the font shape. For zi2zi, it was confirmed that the intended handwritten characters can be output for the input rasterized font by devising the input data and learning conditions. In the displacement information extraction method, characters that could be correctly analyzed were possible to approximate handwritten characters to rasterized fonts in a natural way. However, the entire sentence that was the subject of the experiment collapsed unnaturally, and was not judged to be more beautiful than the original sentence by respondents. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | GAN / Hand Written Character Font / Machine Learning / Energy Functional / Font Generation / Beautiful Character |
| Paper # | EMM2019-115 |
| Date of Issue | 2020-02-27 (EMM) |
| Conference Information | |
| Committee | EMM |
|---|---|
| Conference Date | 2020/3/5(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Image and Sound Quality, Metrics for Perception and Recognition, Human Auditory and Visual System, etc. |
| Chair | Masaki Kawamura(Yamaguchi Univ.) |
| Vice Chair | Motoi Iwata(Osaka Prefecture Univ.) / Tetsuya Kojima(NIT,Tokyo College) |
| Secretary | Motoi Iwata(NIT, Nagano College) / Tetsuya Kojima(Nagase) |
| Assistant | Masaki Inamura(Tokyo Denki Univ.) / Kazuhiro Kono(Kansai Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Enriched MultiMedia |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Poster Presentation] Personalized font system |
| Sub Title (in English) | beautiful character generation with hand writing style |
| Keyword(1) | GAN |
| Keyword(2) | Hand Written Character Font |
| Keyword(3) | Machine Learning |
| Keyword(4) | Energy Functional |
| Keyword(5) | Font Generation |
| Keyword(6) | Beautiful Character |
| 1st Author's Name | Yuto Yamamoto |
| 1st Author's Affiliation | Kyushu Institute of Technology(KIT) |
| 2nd Author's Name | Michiharu Niimi |
| 2nd Author's Affiliation | Kyushu Institute of Technology(KIT) |
| Date | 2020-03-05 |
| Paper # | EMM2019-115 |
| Volume (vol) | vol.119 |
| Number (no) | EMM-463 |
| Page | pp.pp.69-74(EMM), |
| #Pages | 6 |
| Date of Issue | 2020-02-27 (EMM) |