Kaggle Competition: Kuzushiji Character Recognition

We will host a Kaggle competition "Kuzushiji Character Recognition: Opening the Door to A Thousand Years of Japanese Culture" from July 19 to October 14, 2019.

Kaggle competition page: Kuzushiji Recognition - Opening the door to a thousand years of Japanese culture

Related Information

The following summarize the history of kuzushiji recognition, and other basic information.

Kuzushiji Challenge!

Kuzushiji Transcription (Electronic Text) / Translation

Kuzushiji OCR (AI Kuzushiji Recognition)

Second CODH Seminar: Old Japanese Character Challenge - Future of Machine Recognition and Human Transcription -

Examples of Machine Learning (AI) for Kuzushiji

The following is the list of already offered application and services about kuzushiji using machine learning (AI),

Kuzushiji Apps and Services (Search / Recognition / Transcription)

Single Kuzushiji OCR

Related Datasets

Important notice: the following datasets are different from the dataset used in Kaggle competition. Participants of the competition should download the dataset from the Kaggle website.

Kuzushiji Dataset

Kuzushiji Database Search (Hentaigana, Katakana, and Kanji)

KMNIST Dataset (Kuzushiji Dataset for Machine Learning)

Related Symposium

We will hold a symposium also as the award ceremony of Kaggle competition.

Japanese Culture and AI Symposium 2019 (November 11, 2019)

References

  1. Asanobu KITAMOTO, Tarin CLANUWAT, Tomo MIYAZAKI, Kazuaki YAMAMOTO, "Analysis of Character Data: Potential and Impact of Kuzushiji Recognition by Machine Learning", Journal of IEICE (Institute of Electronics, Information, and Communication Engineers), Vol. 102, No. 6, pp. 563-568, doi:10.20676/00000349, June 2019 (in Japanese)
  2. Tarin CLANUWAT, Alex LAMB, Asanobu KITAMOTO, "End-to-End Pre-Modern Japanese Character (Kuzushiji) Spotting with Deep Learning", Proceedings of IPSJ SIG Computers and the Humanities Symposium 2018, pp. 15-20, December 2018 [ Paper ]
  3. Tarin CLANUWAT, Mikel BOBER-IRIZAR, Asanobu KITAMOTO, Alex LAMB, Kazuaki YAMAMOTO, David HA, "Deep Learning for Classical Japanese Literature", NeurIPS 2018 Workshop on Machine Learning for Creativity and Design, December 2018 [ Paper ]
  4. Anh Duc Le, Tarin CLANUWAT, Asanobu KITAMOTO, "A human-inspired recognition system for pre-modern Japanese historical documents", IEEE Access, pp. 1-7, doi:10.1109/ACCESS.2019.2924449, June 2019
  5. Tarin CLANUWAT, Alex LAMB, Asanobu KITAMOTO, "KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning", 15th International Conference on Document Analysis and Recognition (ICDAR2019), pp. (in press), September 2019
  6. Asanobu KITAMOTO, Kazuaki YAMAMOTO, "Construction of trans-disciplinary data platform that explores open data in the humanities", Proceedings of IPSJ SIG Computers and the Humanities Symposium 2016, pp. 117-124, 2016-12 (in Japanese) [ Paper ]
  7. 2nd CODH Seminar: Old Japanese Character Challenge - Future of Machine Recognition and Human Transcription -

Press Release

  1. 【プレスリリース】「くずし字」の認識に世界のAI研究者・技術者が挑戦(2019/07/10) (Joint Support-Center for Data Science Research)
  2. 「くずし字」の認識に世界のAI研究者・技術者が挑戦―全世界的コンペティションをKaggleで7月から開催― (National Institute of Informatics)

Other Competitions

第23回 PRMUアルゴリズムコンテスト

第23回 PRMUアルゴリズムコンテスト くずし字認識チャレンジ2019 (2019-08-31締切)