GLOSS
发表于 2025-3-26 23:22:38
http://reply.papertrans.cn/29/2849/284810/284810_31.png
直觉好
发表于 2025-3-27 03:22:00
http://reply.papertrans.cn/29/2849/284810/284810_32.png
袋鼠
发表于 2025-3-27 07:40:08
Fully Automatic Virtual Unwrapping Method for Documents Imaged by X-Ray Tomography CT-OCR-2022 dataset, utilizing a novel criterion for geometric distortion evaluation. Enriched with marker coordinates, the dataset facilitates future algorithm assessments. Accompanying source codes for the proposed algorithms and evaluation criterion are publicly available.
Ergots
发表于 2025-3-27 10:35:33
DELINE8K: A Synthetic Data Pipeline for the Semantic Segmentation of Historical Documentsument .lement .ayer .tegration .nsemble 8K, or DELINE8K dataset (DELINE8K is available at .). Our customized dataset exhibits superior performance on the NAFSS benchmark, demonstrating it as a promising tool in further research.
optional
发表于 2025-3-27 14:14:55
http://reply.papertrans.cn/29/2849/284810/284810_35.png
Devastate
发表于 2025-3-27 20:34:20
beled all text-line images for the HHD-Ethiopic dataset, and an expert supervisor double-checked them. We assessed human-level recognition performance and compared it with state-of-the-art (SOTA) OCR models using the Character Error Rate (CER) and Normalized Edit Distance (NED) metrics. Our results
collateral
发表于 2025-3-28 01:28:46
http://reply.papertrans.cn/29/2849/284810/284810_37.png
暗语
发表于 2025-3-28 05:56:03
http://reply.papertrans.cn/29/2849/284810/284810_38.png
祖先
发表于 2025-3-28 07:06:11
http://reply.papertrans.cn/29/2849/284810/284810_39.png
SYN
发表于 2025-3-28 11:02:59
http://reply.papertrans.cn/29/2849/284810/284810_40.png