@inproceedings{bc708f381994407b8297731316c13bf8,
title = "Simplifying the reading of historical manuscripts",
abstract = "Complex document layouts pose prominent challenges for document image understanding algorithms. These layouts impose irregularities on the location of text paragraphs which consequently induces difficulties in reading the text. In this paper we present a robust framework for analyzing historical manuscripts with complex layouts. This framework aims to provide a convenient reading experience for historians through topnotch algorithms for text localization, classification and dewarping. We segment text into spatially coherent regions and text-lines using texture-based filters and refine this segmentation by exploiting Markov Random Fields (MRFs). A principled technique is presented for dewarping curvy text regions using a non-linear geometric transformation. The framework has been validated using a subset of a publicly available dataset of historical documents and it provided promising results.",
author = "Abedelkadir Asi and Rafi Cohen and Klara Kedem and Jihad El-Sana",
note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 13th International Conference on Document Analysis and Recognition, ICDAR 2015 ; Conference date: 23-08-2015 Through 26-08-2015",
year = "2015",
month = nov,
day = "20",
doi = "10.1109/ICDAR.2015.7333877",
language = "English",
series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
publisher = "Institute of Electrical and Electronics Engineers",
pages = "826--830",
booktitle = "13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings",
address = "United States",
}