Automatic layout analysis has proven to be extremely important in the process of digitization of large amounts of documents. In this paper we present a mixed approach to layout analysis, introducing a SVM-aided layout segmentation process and a classification process based on local and geometrical features. The final output of the automatic analysis algorithm is a complete and structured annotation in JSON format, containing the digitalized text as well as all the references to the illustrations of the input page, and which can be used by visualization interfaces as well as annotation interfaces. We evaluate our algorithm on a large dataset built upon the first volume of the “Enciclopedia Treccani”.
Layout analysis and content classification in digitized books / Corbelli, Andrea; Baraldi, Lorenzo; Balducci, Fabrizio; Grana, Costantino; Cucchiara, Rita. - ELETTRONICO. - 701:(2017), pp. 153-165. (Intervento presentato al convegno 12th Italian Research Conference on Digital Libraries, IRCDL 2016 tenutosi a Firenze nel Feb. 4-5) [10.1007/978-3-319-56300-8_14].
Layout analysis and content classification in digitized books
CORBELLI, ANDREA;BARALDI, LORENZO;BALDUCCI, FABRIZIO;GRANA, Costantino;CUCCHIARA, Rita
2017
Abstract
Automatic layout analysis has proven to be extremely important in the process of digitization of large amounts of documents. In this paper we present a mixed approach to layout analysis, introducing a SVM-aided layout segmentation process and a classification process based on local and geometrical features. The final output of the automatic analysis algorithm is a complete and structured annotation in JSON format, containing the digitalized text as well as all the references to the illustrations of the input page, and which can be used by visualization interfaces as well as annotation interfaces. We evaluate our algorithm on a large dataset built upon the first volume of the “Enciclopedia Treccani”.File | Dimensione | Formato | |
---|---|---|---|
2016_IRCDL.pdf
Open access
Tipologia:
AAM - Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
4.81 MB
Formato
Adobe PDF
|
4.81 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
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