Proposed method of acquiring train data for early-modern Japanese printed character recognizers
The Journal of Supercomputing · 21.04.2025 · 81 (6)
DOI: 10.1007/s11227-024-06866-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Supercomputing, online erschienen am 21.04.2025. Verfasst von Norie Koiso und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 16 Literaturangaben.
Abstract (Originalsprache)
The National Diet Library maintains a digital archive of approximately 400,000 historical texts from the Meiji to early Showa periods (1868–1935), representing a significant corpus of Japanese cultural heritage. While these materials are digitally preserved as high-resolution images, the lack of machine-readable text severely constrains their accessibility and scholarly utility. This limitation particularly impacts early-modern Japanese printed texts, where conventional optical character recognition systems achieve only 60–75% accuracy due to the unique characteristics of historical typography. Current approaches to digitizing these materials face significant challenges: manual transcription is prohibitively expensive for large-scale application, while automated methods struggle with the irregular features of early-modern printed characters, including non-standardized character forms, ink bleeding, and letterpress artifacts. Furthermore, the scarcity of available character samples, particularly for less frequent characters, hinders the development of robust recognition systems. This study presents a novel methodology for enhancing early-modern Japanese character recognition through a two-fold approach: (1) utilizing CycleGAN-generated synthetic characters to augment limited historical samples and (2) developing an optimal mixing strategy between original, generated, and modern characters. Our approach achieves recognition rates of up to 97.81%, significantly outperforming conventional methods while addressing the critical challenge of data scarcity in historical character recognition. Experimental validation demonstrated that our proposed method achieved substantial improvements in recognition accuracy: incorporating generated characters increased recognition rates from 93.43 to 97.81% (p < 0.001) when sufficient original characters were available, and maintained robust performance (94.90%) even with limited historical samples. The model achieved AUC scores consistently above 0.999 across all experiments, demonstrating high reliability in character discrimination regardless of the data composition.
Zitieren
APA
Koiso, N., Takemoto, Y., Ishikawa, Y., & Takata, M. (2025). Proposed method of acquiring train data for early-modern Japanese printed character recognizers. The Journal of Supercomputing, 81(6). https://doi.org/10.1007/s11227-024-06866-4
Vancouver
Koiso N, Takemoto Y, Ishikawa Y, Takata M. Proposed method of acquiring train data for early-modern Japanese printed character recognizers. The Journal of Supercomputing. 2025;81(6). doi:10.1007/s11227-024-06866-4
BibTeX
@article{Koiso2025,
author = {Koiso, Norie and Takemoto, Yuki and Ishikawa, Yu and Takata, Masami},
title = {Proposed method of acquiring train data for early-modern Japanese printed character recognizers},
journal = {The Journal of Supercomputing},
year = {2025},
volume = {81},
number = {6},
doi = {10.1007/s11227-024-06866-4}
}
EUVIMED