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.
Advances in Neural Information Processing Systems37, 107984– 108011 (2024)
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.