This work is a project to create Kanji (Chinese characters) by deep learning, which is different from the conventional method of creating Kanji. It uses a text2image based model to infer and visualize a compressed Kanji for an arbitrary character string or text input. This work attempts to give Kanji characters to sentences and character strings that have not been given specific Kanji characters. It also brings new interpretations to concepts that already have Kanji characters.
September 15th, 2021.
Scott Allen (Direction, Machine learning, Visual programming)
Keito Takaishi (Machine learning, Visual programming)
Asuka Ishii (Machine learning)
Kazufumi Shibuya (Machine learning, Visual programming)
Santa Naruse (Machine Learning)
Muhan Li (Support)
Atsuya Kobayashi (Sound)
Nao Tokui (Direction)
Soshi Yamaguchi (Sound equipment cooperation)
Keio University SFC Computational Creativity Lab (Nao Tokui Lab)