34 International Journal of Mobile Computing and Multimedia Communications, 4(3), 34-53, July-September 2012
Copyright © 2012, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. Copyright © 2012, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.
Keywords: Automatic Evaluation, Document Pre-Processing, Evaluation Metrics, Ground-Truth
Generation, Next Generation Network Application
INTRODUCTION
The communication industry continues to
improve the quality of its products. This im-
provement is shown in the functional network
architecture, that is, the physical architecture of
the network elements, as well as in the interac-
tion between different service domains. The first
objective of the telecommunication operators
was the improvement of the network infrastruc-
ture. In the last few years, it has been proved that
without new services, it is difficult to achieve
success (Xu et al., 2011). The Next Generation
Operation Support System (NGOSS) has been
considered as a possible solution for service
providers. Due to improvements in the next
generation network, most applications have
Collaborative Access to
Ancient Documents:
Towards a Distributed Comparison
of Pre-Processing Approaches
Ines Ben Messaoud Ben Arbia, École Nationale d’Ingénieurs de Tunis, Tunisia
Haikal El Abed, Technische Universität Braunschweig, Germany
Volker Märgner, Technische Universität Braunschweig, Germany
Hamid Amiri, École Nationale d’Ingénieurs de Tunis, Tunisia
ABSTRACT
With the evolution of the next generation networks several applications have emerged to be used through the
web. Applications allowing the analysis and the recognition of documents are emerged to be used through
Internet. Document pre-processing output may affect the effciency of document analysis and recognition
systems. In order to ameliorate the effciency of such systems, an objective evaluation of pre-processing steps
is necessary. The authors propose a new framework for automatic evaluation of binarization approaches. The
evaluation of binarization approaches is based on the comparison between binary images and their ground-
truths. For that reason a method for the generation of ground-truth is proposed. This method is evaluated using
the benchmarking dataset DIBCO 2009. The comparison between binarization methods’ results is based on
several evaluation metrics as FM and PSNR. The proposed framework is tested on printed images (250 images)
from the Google-Books collection and on handwritten images (60 images) from the IAM historical database.
DOI: 10.4018/jmcmc.2012070103