Kotenseki Image Search
Yusuke Matsui
- National Institute of Informatics (NII)
Chairath Sirirattanapol
- Asian Institute of Technology (AIT)
Shin'ichi Satoh
- National Institute of Informatics (NII)
Kuninori Matsuda
- National Institute of Japanese Literature (NIJL)
Kazuaki Yamamoto
- National Institute of Japanese Literature (NIJL)
Abstract
Kotenseki is defined as Japanese classic literature before the Meiji era. The team of NII and NIJL is developing a content-based image search system for kotenseki images. With computer vision techniques, we seek a way to evaluate kotenseki images quantitatively, and aim for new discoveries in Japanese literature.
Publication
-
Deep Image Retrieval Applied on Kotenseki Ancient Japanese Literature
Chairath Sirirattanapol, Yusuke Matsui, Shin'ichi Satoh, Kuninori Matsuda, Kazuaki Yamamoto
IEEE International Workshop on Machine Learning and Computing for Visual Semantic Analysis (MLCSA), 2017
Featured (in Japanese)
- Internet Watch (2017.6.8)
- IT Media (2017.6.9)
- Oricon News (2017.6.9)
- Exciteニュース (2017.6.12)
- 日刊工業新聞 (2017.6.16)
- 科学新聞 2面 (2017.6.16)
- Hazard Lab (2017.6.18)
- 東京新聞 朝刊4面 (2017.6.26)
- 日本産業新聞 朝刊8面 (2017.7.5)
- 朝日新聞 朝刊23面 (2017.7.6)
- 読売新聞 朝刊17面 (2017.7.16)