@inproceedings{d7ce30214b934b04b40f0e6a09a4521a,
title = "Layout analysis on challenging historical arabic manuscripts using siamese network",
abstract = "This paper presents layout analysis for historical Arabic documents using siamese network. Given pages from different documents, we divide them into patches of similar sizes. We train a siamese network model that takes as an input a pair of patches and gives as an output a distance that corresponds to the similarity between the two patches. We used the trained model to calculate a distance matrix which in turn is used to cluster the patches of a page as either main text, side text or a background patch. We evaluate our method on challenging historical Arabic manuscripts dataset and report the F-measure. We show the effectiveness of our method by comparing with other works that use deep learning approaches, and show that we have state of art results.",
keywords = "Clustering, Historical Arabic Documents, Layout Analysis, Siamese Network",
author = "Reem Alaasam and Berat Kurar and Jihad El-Sana",
note = "Funding Information: This research was supported in part by Frankel Center for Computer Science at Ben-Gurion University of the Negev. One of the authors, Reem Alaasam, is a fellow of the Ariane de Rothschild Women Doctoral Program, and would like to thank them for their support. Publisher Copyright: {\textcopyright} 2019 IEEE.; 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 ; Conference date: 20-09-2019 Through 25-09-2019",
year = "2019",
month = sep,
day = "1",
doi = "10.1109/ICDAR.2019.00123",
language = "English",
series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
publisher = "IEEE Computer Society",
pages = "738--742",
booktitle = "Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019",
address = "United States",
}