The main interest in paleographer work is to relate the culture and the writing styles of ancient manuscripts analyzing the morphology of scripts. Unfortunately, often experts disagree on the analysis methods. For this reason, an user-independent system based on statistical methods can be very helpful for experts on determining which morphological features are relevant for the description of the writing styles with respect to time (document epoch) and space (geographic area). We propose a System for Paleographic Inspections (SPI), which, using a relatively new concept of distance (tangent distance) and statistical based algorithms, collects a set of prototype models for each character type (tangent subspace model), such that each one represents information about the general morphology of a character style. Several tools for the analysis of stored manuscripts and classification of unlabeled manuscripts are implemented into the system. A preliminary test on 37 different book manuscripts and more than 7000 characters extracted from them demonstrated the effectiveness of the system.

SPI: A System for Paleographic Inspections

SIMI, MARIA;
1999-01-01

Abstract

The main interest in paleographer work is to relate the culture and the writing styles of ancient manuscripts analyzing the morphology of scripts. Unfortunately, often experts disagree on the analysis methods. For this reason, an user-independent system based on statistical methods can be very helpful for experts on determining which morphological features are relevant for the description of the writing styles with respect to time (document epoch) and space (geographic area). We propose a System for Paleographic Inspections (SPI), which, using a relatively new concept of distance (tangent distance) and statistical based algorithms, collects a set of prototype models for each character type (tangent subspace model), such that each one represents information about the general morphology of a character style. Several tools for the analysis of stored manuscripts and classification of unlabeled manuscripts are implemented into the system. A preliminary test on 37 different book manuscripts and more than 7000 characters extracted from them demonstrated the effectiveness of the system.
1999
Aiolli, F.; Simi, Maria; Sona, D.; Sperduti, A.; Starita, A.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/163889
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact