Please use this identifier to cite or link to this item:
Title: A model for the gray-intensity distribution of historical handwritten documents and its application for binarization
Author: Castillo-Barrera, F.-E.
Duran-Limon, H.A.
Medina-Ramirez, C.
Rodriguez-Rocha, B.
Issue Date: 2013
Abstract: Different methods and methodologies have been developed for building ontologies. However, neither of these methods consider to build an ontology with characteristics of an electronic document management system (EDMS) nor define the basic classes to begin the ontology. In this paper we propose a method, called "OntoDocMan", to build an ontology-based EDMS which captures the knowledge associated with a company's processes related to a quality standard. We leverage the use of ontology tools, such as Protégé, to obtain the functionality of an EDMS. Our method complements and details the On-To-Knowledge methodology during its ontology development phase. The essential point of our method is to make it easy to develop an EDMS for quality standards by means of an ontology-based system. The OntoDocMan method is illustrated by a case study for developing an ontology based on the ISO/TS 16949, which is a Technical Specification (TS) and we show that the Ontology system is friendly and easy to use as any EDMS. Different from common EDMS, our ontology-based EDMS is developed without any programming. In addition, we have discovered that this kind of ontology-based EDMS is an excellent tool for helping auditors to search and validate information, besides new employees can learn about the company's processes. " 2012 Springer Science+Business Media, LLC.",,,,,,"10.1007/s10489-012-0360-1",,,"","",,,,,,"1",,"Applied Intelligence",,"99
WOS",,,,,,"Artificial intelligence; Automotive industry; Electronic document management; ISO/TS 16949; Method; Ontology; Quality management systems",,,,,,"A method for building ontology-based electronic document management systems for quality standards - The case study of the ISO/TS 16949:2002 automotive standard",,"Article" "40796","123456789/35008",,"Ramírez-Ortegón, M.A., División Académica de Ciencias Básicas, UJAT, Apartado Postal 24, 86690 Cunduacán, Tabasco, Mexico; Ramírez-Ramírez, L.L., Instituto Tecnológico Autónomo de México (ITAM), Rio Hondo No 1. Col. Progreso Tizapán, D.F., 01080 Mexico, Mexico; Messaoud, I.B., Laboratoire des Systèmes et Traitement de Signal, LSTS Ecole Nationale dIngénieurs de Tunis, ENIT Tunis, Tunis, Tunisia; Morgner, V., Institut for Nachrichtentechnik, Technische Universityt Braunschweig, Schleinitzstrasse 22, 38106 Braunschweig, Germany; Cuevas, E., Departamento de Ciencias Computacionales, Universidad de Guadalajara, Av. Revolución 1500, Guadalajara, Jalisco, Mexico; Rojas, R., Institut for Informatik, Freie Universityt Berlin, Takustr. 7, 14195 Berlin, Germany",,"Ramirez-Ortegon, M.A.
Ramirez-Ramirez, L.L.
Messaoud, I.B.
Margner, V.
Cuevas, E.
Rojas, R.",,"2014",,"In this article, our goal is to describe mathematically and experimentally the gray-intensity distributions of the fore- and background of handwritten historical documents. We propose a local pixel model to explain the observed asymmetrical gray-intensity histograms of the fore- and background. Our pixel model states that, locally, the gray-intensity histogram is the mixture of gray-intensity distributions of three pixel classes. Following our model, we empirically describe the smoothness of the background for different types of images. We show that our model has potential application in binarization. Assuming that the parameters of the gray-intensity distributions are correctly estimated, we show that thresholding methods based on mixtures of lognormal distributions outperform thresholding methods based on mixtures of normal distributions. Our model is supported with experimental tests that are conducted with extracted images from DIBCO 2009 and H-DIBCO 2010 benchmarks. We also report results for all four DIBCO benchmarks. " 2013 Springer-Verlag Berlin Heidelberg.
Appears in Collections:Producción científica UdeG

Files in This Item:
There are no files associated with this item.

Items in RIUdeG are protected by copyright, with all rights reserved, unless otherwise indicated.