ダウンロード数: 230
このアイテムのファイル:
ファイル | 記述 | サイズ | フォーマット | |
---|---|---|---|---|
ADADA2020_1A_1.pdf | 701.67 kB | Adobe PDF | 見る/開く |
タイトル: | Evaluation of Art Style Using AI and Psychological Experiments |
著者: | Hung, Mai Cong Nakatsu, Ryohei Tosa, Naoko Kusumi, Takashi |
著者名の別形: | 中津, 良平 土佐, 尚子 楠見, 孝 |
キーワード: | Cycle GAN art style psychological evaluation |
発行日: | Dec-2020 |
出版者: | Asia Digital Art and Design Association |
誌名: | Proceedings of ADADA2020 |
論文番号: | 1A_1 |
抄録: | GANs (Generative adversarial networks) is a new AI technology that has the capability of achieving transformation between two image sets. Using GANs we have carried out a comparison among several art sets with different art styles. We have prepared four image sets; a flower image set with Impressionism art style, one with the Western abstract art style, one with Chinese figurative art style, and one with the art style of Naoko Tosa, one of the authors. Using these four sets we have carried out a psychological experiment to evaluate the difference between these four sets. We have found that abstract drawings and figurative drawings are judged to be different, figurative drawings in West and East were judged to be similar, and Naoko Tosa’s artworks are similar to the Western abstract artworks. |
記述: | [ADADA+CUMULUS 2020 (International Conference for Asia Digital Art and Design 2020)] Fully Virtual Conference, 2020/12/14-16. |
著作権等: | © Authors. This is not the published version. Please cite only the published version. この論文は出版社版でありません。引用の際には出版社版をご確認ご利用ください。 |
URI: | http://hdl.handle.net/2433/265845 |
関連リンク: | http://adada.info/2020/ |
出現コレクション: | 学術雑誌掲載論文等 |
このリポジトリに保管されているアイテムはすべて著作権により保護されています。