In this paper we propose an approach for Document Layout Analysis based on local correlation features. We identify and extract illustrations in digitized documents by learning the discriminative patterns of textual and pictorial regions. The proposal has been demonstrated to be effective on historical datasets and to outperform the state-of-the-art in presence of challenging documents with a large variety of pictorial elements.

Illustrations Segmentation in Digitized Documents Using Local Correlation Features / Coppi, Dalia; Grana, Costantino; Cucchiara, Rita. - In: PROCEDIA COMPUTER SCIENCE. - ISSN 1877-0509. - ELETTRONICO. - 38:C(2014), pp. 76-83. (Intervento presentato al convegno 10th Italian Research Conference on Digital Libraries tenutosi a Padova nel Jan. 30-31) [10.1016/j.procs.2014.10.014].

Illustrations Segmentation in Digitized Documents Using Local Correlation Features

COPPI, DALIA;GRANA, Costantino;CUCCHIARA, Rita
2014

Abstract

In this paper we propose an approach for Document Layout Analysis based on local correlation features. We identify and extract illustrations in digitized documents by learning the discriminative patterns of textual and pictorial regions. The proposal has been demonstrated to be effective on historical datasets and to outperform the state-of-the-art in presence of challenging documents with a large variety of pictorial elements.
2014
10th Italian Research Conference on Digital Libraries
Padova
Jan. 30-31
38
76
83
Coppi, Dalia; Grana, Costantino; Cucchiara, Rita
Illustrations Segmentation in Digitized Documents Using Local Correlation Features / Coppi, Dalia; Grana, Costantino; Cucchiara, Rita. - In: PROCEDIA COMPUTER SCIENCE. - ISSN 1877-0509. - ELETTRONICO. - 38:C(2014), pp. 76-83. (Intervento presentato al convegno 10th Italian Research Conference on Digital Libraries tenutosi a Padova nel Jan. 30-31) [10.1016/j.procs.2014.10.014].
File in questo prodotto:
File Dimensione Formato  
2014IRCDL.pdf

Open access

Tipologia: Versione originale dell'autore proposta per la pubblicazione
Dimensione 2.97 MB
Formato Adobe PDF
2.97 MB Adobe PDF Visualizza/Apri
1-s2.0-S187705091401374X-main.pdf

Open access

Tipologia: Versione pubblicata dall'editore
Dimensione 4.95 MB
Formato Adobe PDF
4.95 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1060472
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 3
social impact