Morphological waveform coding for writer identification

dc.contributor.author	Ζώης, Ηλίας Ν.	el
dc.contributor.author	Αναστασόπουλος, Βασίλειος	el
dc.date.accessioned	2015-01-09T11:00:16Z
dc.date.available	2015-01-09T11:00:16Z
dc.date.issued	2015-01-09
dc.identifier.uri	http://hdl.handle.net/11400/3608
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.source	http://www.elsevier.com	en
dc.subject	Writer identification
dc.subject	Morphological features
dc.subject	Ταυτοποίηση συγγραφέα
dc.subject	Μορφολογικά χαρακτηριστικά
dc.title	Morphological waveform coding for writer identification	en
heal.type	journalArticle
heal.classification	Electrical engineering
heal.classification	Electronics
heal.classification	Ηλεκτρολογική μηχανική
heal.classification	Ηλεκτρονική
heal.classificationURI	http://skos.um.es/unescothes/C01311
heal.classificationURI	http://zbw.eu/stw/descriptor/10455-2
heal.classificationURI	N/A-Ηλεκτρολογική μηχανική
heal.classificationURI	N/A-Ηλεκτρονική
heal.identifier.secondary	doi:10.1016/S0031-3203(99)00063-1
heal.language	en
heal.access	free
heal.recordProvider	Τ.Ε.Ι. Αθήνας. Σχολή Τεχνολογικών Εφαρμογών. Τμήμα Ηλεκτρονικών Μηχανικών Τ.Ε.	el
heal.publicationDate	2000
heal.bibliographicCitation	Zois, E. and Anastassopoulos, V. (March 2000). Morphological waveform coding for writer identification. Pattern Recognition. 33(3). pp. 385-398. Elsevier Science Ltd. Available from: http://www.sciencedirect.com/ [Accessed 09/12/1999]	en
heal.abstract	Writer identification is carried out using handwritten text. The feature vector is derived by means of morphologically processing the horizontal profiles (projection functions) of the words. The projections are derived and processed in segments in order to increase the discrimination efficiency of the feature vector. Extensive study of the statistical properties of the feature space is provided. Both Bayesian classifiers and neural networks are employed to test the efficiency of the proposed feature. The achieved identification success using a long word exceeds 95%.	en
heal.publisher	Elsevier Science Ltd	en
heal.journalName	Pattern Recognition	en
heal.journalType	peer-reviewed
heal.fullTextAvailability	true