DKDS is a new annotated benchmark dataset of degraded Kuzushiji documents with seals for detection and binarization tasks, with baselines from YOLO variants and GAN methods.
In: International Confer- ence on Learning Representations (2021) [13]国文学研 究資料館:日本古典籍く ず し 字データセ ット(2016)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DKDS: A Benchmark Dataset of Degraded Kuzushiji Documents with Seals for Detection and Binarization
DKDS is a new annotated benchmark dataset of degraded Kuzushiji documents with seals for detection and binarization tasks, with baselines from YOLO variants and GAN methods.