@conference {kumar_handwritten_2010,
title = {Handwritten {Arabic} {Text} {Line} {Segmentation} {Using} {Affinity} {Propagation}},
booktitle = {Proceedings of the 9th {IAPR} {International} {Workshop} on {Document} {Analysis} {Systems}},
series = {{DAS} {\textquoteright}10},
year = {2010},
pages = {135{\textendash}142},
publisher = {ACM},
organization = {ACM},
address = {New York, NY, USA},
abstract = {In this paper, we present a novel graph-based method for extracting handwritten text lines in monochromatic Arabic document images. Our approach consists of two steps - Coarse text line estimation using primary components which define the line and assignment of diacritic components which are more difficult to associate with a given line. We first estimate local orientation at each primary component to build a sparse similarity graph. We then, use a shortest path algorithm to compute similarities between non-neighboring components. From this graph, we obtain coarse text lines using two estimates obtained from Affinity propagation and Breadth-first search. In the second step, we assign secondary components to each text line. The proposed method is very fast and robust to non-uniform skew and character size variations, normally present in handwritten text lines. We evaluate our method using a pixel-matching criteria, and report 96\% accuracy on a dataset of 125 Arabic document images. We also present a proximity analysis on datasets generated by artificially decreasing the spacings between text lines to demonstrate the robustness of our approach.},
keywords = {affinity propagation, Arabic, Arabic documents, breadth-first search, clustering, Dijkstra{\textquoteright}s shortest path algorithm, Handwritten Documents, line detection, text line segmentation},
isbn = {978-1-60558-773-8},
doi = {10.1145/1815330.1815348},
url = {http://doi.acm.org/10.1145/1815330.1815348},
author = {Kumar, Jayant and Abd-Almageed, Wael and Kang, Le and Doermann, David}
}