Presentation | 2021-10-08 Analysis of Writing Style on Wood Slips of the Chinese Han period Using Deep Generative Model Chiang Meng Yuan, Soh Yoshida, Takao Fujita, Mitsuji Muneyasu, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we develop a method to objectively analyze the calligraphic styles of wood slips excavated in Northwestern China. In this paper, we propose a method to quantify the degree of collapse of the Chinese characters by measuring the degree of dissociation using a deep generative model. Specifically, we introduce the Anomaly detection Generative Adversarial Network (AnoGAN), which is trained by normal data and judges abnormal data based on the reconstruction error when the other data is input. First, we train the GAN using an image of a character written in Clerical-Script calligraphy as training data. Next, we calculate the anomaly value of the characters based on the difference between the Cursive-Script calligraphy characters and the generated character images, and then calculate the degree of collapse. In our experiments, we created datasets consisting of wooden slips from the Han Period and showed that the proposed method can quantify the degree of misalignment between Clerical-Script of neat font and Cursive-Script of scrawl font. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | wood slips / writing style analysis / Generative Adversarial Network / anomaly detection |
Paper # | SIS2021-20 |
Date of Issue | 2021-09-30 (SIS) |
Conference Information | |
Committee | SIS / ITE-BCT |
---|---|
Conference Date | 2021/10/7(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | System Implementation Technology, Short Range Wireless Systems, Smart Multimedia Systems, Broadcasting Technology, etc. |
Chair | Noriaki Suetake(Yamaguchi Univ.) / Kyoichi Saito(NHK) |
Vice Chair | Tomoaki Kimura(Kanagawa Inst. of Tech.) / Naoto Sasaoka(Tottori Univ.) / Hidekazu Murata(Kyoto Univ.) / Hajime Saito(TV Tokyo) |
Secretary | Tomoaki Kimura(National Inst. of Tech., Ube College) / Naoto Sasaoka(NTT) / Hidekazu Murata(NHK) / Hajime Saito(TV Asahi) |
Assistant | Soh Yoshida(Kansai Univ.) / Yoshiaki Makabe(Kanagawa Inst. of Tech.) / Hiroshi Tsutsui(Hokkaido Univ.) / Akihiro Tanabe(NTT) / Toshimitsu Kobayashi(NBN) |
Paper Information | |
Registration To | Technical Committee on Smart Info-Media Systems / Technical Group on Broadcasting and Communication Technologies |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Analysis of Writing Style on Wood Slips of the Chinese Han period Using Deep Generative Model |
Sub Title (in English) | |
Keyword(1) | wood slips |
Keyword(2) | writing style analysis |
Keyword(3) | Generative Adversarial Network |
Keyword(4) | anomaly detection |
1st Author's Name | Chiang Meng Yuan |
1st Author's Affiliation | Kansai University(Kansai Univ.) |
2nd Author's Name | Soh Yoshida |
2nd Author's Affiliation | Kansai University(Kansai Univ.) |
3rd Author's Name | Takao Fujita |
3rd Author's Affiliation | Kansai University(Kansai Univ.) |
4th Author's Name | Mitsuji Muneyasu |
4th Author's Affiliation | Kansai University(Kansai Univ.) |
Date | 2021-10-08 |
Paper # | SIS2021-20 |
Volume (vol) | vol.121 |
Number (no) | SIS-190 |
Page | pp.pp.54-59(SIS), |
#Pages | 6 |
Date of Issue | 2021-09-30 (SIS) |