skip to main content
Idioma:

U-Net Architecture for Ancient Handwritten Chinese Character Detection in Han Dynasty Wooden Slips

SHIMOYAMA, Hojun ; YOSHIDA, Soh ; FUJITA, Takao ; MUNEYASU, Mitsuji

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2023/11/01, Vol.E106.A(11), pp.1406-1415 [Periódico revisado por pares]

Tokyo: The Institute of Electronics, Information and Communication Engineers

Texto completo disponível

Citações Citado por
  • Título:
    U-Net Architecture for Ancient Handwritten Chinese Character Detection in Han Dynasty Wooden Slips
  • Autor: SHIMOYAMA, Hojun ; YOSHIDA, Soh ; FUJITA, Takao ; MUNEYASU, Mitsuji
  • Assuntos: Artificial neural networks ; Aspect ratio ; Boundaries ; Documents ; Handwriting ; handwritten Chinese character detection ; historical document analysis ; Machine learning ; U-Net ; Wood construction ; wooden slips
  • É parte de: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2023/11/01, Vol.E106.A(11), pp.1406-1415
  • Descrição: Recent character detectors have been modeled using deep neural networks and have achieved high performance in various tasks, such as text detection in natural scenes and character detection in historical documents. However, existing methods cannot achieve high detection accuracy for wooden slips because of their multi-scale character sizes and aspect ratios, high character density, and close character-to-character distance. In this study, we propose a new U-Net-based character detection and localization framework that learns character regions and boundaries between characters. The proposed method enhances the learning performance of character regions by simultaneously learning the vertical and horizontal boundaries between characters. Furthermore, by adding simple and low-cost post-processing using the learned regions of character boundaries, it is possible to more accurately detect the location of a group of characters in a close neighborhood. In this study, we construct a wooden slip dataset. Experiments demonstrated that the proposed method outperformed existing character detection methods, including state-of-the-art character detection methods for historical documents.
  • Editor: Tokyo: The Institute of Electronics, Information and Communication Engineers
  • Idioma: Inglês
Voltar para lista de resultados
Ir para página anteriorAnterior Resultado  3 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.