A TaLISMAN: Automatic Text and LIne Segmentation of historical MANuscripts

Pintus, Ruggero; Yang, Ying; Gobbetti, Enrico; Rushmeier, Holly

A TaLISMAN: Automatic Text and LIne Segmentation of historical MANuscripts

Files

035-044.pdf (3.28 MB)

paper1001_e-paper.pptx (4.66 MB)

Date

2014

Authors

Pintus, Ruggero
Yang, Ying
Gobbetti, Enrico
Rushmeier, Holly

Publisher

The Eurographics Association

Abstract

Historical and artistic handwritten books are valuable cultural heritage (CH) items, as they provide information about tangible and intangible cultural aspects from the past. Massive digitization projects have made these kind of data available to a world-wide population, and pose real challenges for automatic processing. In this scenario, document layout analysis plays a significant role, being a fundamental step of any document image understanding system. In this paper, we present a completely automatic algorithm to perform a robust text segmentation of old handwritten manuscripts on a per-book basis, and we show how to exploit this outcome to find two layout elements, i.e., text blocks and text lines. Our proposed technique have been evaluated on a large and heterogeneous corpus content, and our experimental results demonstrate that this approach is efficient and reliable, even when applied to very noisy and damaged books.

        @inproceedings{:10.2312/gch.20141302
https::/diglib.eg.org/handle/10.2312/gch.20141302.035-044
,
booktitle = {Eurographics Workshop on Graphics and Cultural Heritage
},
editor = {Reinhard Klein and Pedro Santos
},
title = {{A TaLISMAN: Automatic Text and LIne Segmentation of historical MANuscripts
}},
author = {Pintus, Ruggero and 
Yang, Ying and 
Gobbetti, Enrico and 
Rushmeier, Holly
},
year = {2014
},
publisher = {The Eurographics Association
},
ISSN = {2312-6124
},
ISBN = {978-3-905674-63-7
},
DOI = {/10.2312/gch.20141302
https://diglib.eg.org/handle/10.2312/gch.20141302.035-044
}
}