Abstract - Artificial neural networks have been extensively applied to document analysis and recognition. Most efforts have been devoted to the recognition of isolated handwritten and printed characters with widely recognized successful results. However, many other document processing tasks, like preprocessing, layout analysis, character segmentation, word recognition, and signature verification, have been effectively faced with very promising results. This paper surveys the most significant problems in the area of offline document image processing, where connectionist-based approaches have been applied. Similarities and differences between approaches belonging to different categories are discussed. A particular emphasis is given on the crucial role of prior knowledge for the conception of both appropriate architectures and learning algorithms. Finally, the paper provides a critical analysis on the reviewed approaches and depicts the most promising research guidelines in the field. In particular, a second generation of connectionist-based models are foreseen which are based on appropriate graphical representations of the learning environment.

Artificial Neural Networks for Document Analysis and recognition / S. Marinai; M. Gori; G. Soda. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - STAMPA. - 27:(2005), pp. 23-35. [10.1109/TPAMI.2005.4]

Artificial Neural Networks for Document Analysis and recognition

MARINAI, SIMONE;SODA, GIOVANNI
2005

Abstract

Abstract - Artificial neural networks have been extensively applied to document analysis and recognition. Most efforts have been devoted to the recognition of isolated handwritten and printed characters with widely recognized successful results. However, many other document processing tasks, like preprocessing, layout analysis, character segmentation, word recognition, and signature verification, have been effectively faced with very promising results. This paper surveys the most significant problems in the area of offline document image processing, where connectionist-based approaches have been applied. Similarities and differences between approaches belonging to different categories are discussed. A particular emphasis is given on the crucial role of prior knowledge for the conception of both appropriate architectures and learning algorithms. Finally, the paper provides a critical analysis on the reviewed approaches and depicts the most promising research guidelines in the field. In particular, a second generation of connectionist-based models are foreseen which are based on appropriate graphical representations of the learning environment.
2005
27
23
35
S. Marinai; M. Gori; G. Soda
File in questo prodotto:
File Dimensione Formato  
TPAMI05.pdf

Accesso chiuso

Tipologia: Versione finale referata (Postprint, Accepted manuscript)
Licenza: Tutti i diritti riservati
Dimensione 1.9 MB
Formato Adobe PDF
1.9 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/310911
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 142
  • ???jsp.display-item.citation.isi??? 93
social impact