A robust and efficient algorithm for Chinese historical document analysis and recognition

This paper presents a novel and efficient algorithm for Chinese historical document understanding, incorporating three key components: a multi-oriented text detector, a dual-path learning-based text recognizer, and a heuristic-based reading order predictor.

Detalles Bibliográficos
Autores principales: Liu, Chongyu, Jian, Cheng, Huang, Jiarong, Yang, Wentao, Shi, Yongxin, Jiang, Qing, Jin, Lianwen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2023
Materias:
PERSPECTIVE
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10246825/
https://www.ncbi.nlm.nih.gov/pubmed/37292085
http://dx.doi.org/10.1093/nsr/nwad115

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10246825/
https://www.ncbi.nlm.nih.gov/pubmed/37292085
http://dx.doi.org/10.1093/nsr/nwad115

Ejemplares similares