Zur Seitenansicht
 

Titelaufnahme

Titel
ICDAR2017 Competition on Historical Document Writer Identification (Historical-WI)
Verfasser / Verfasserin Fiel, Stefan ; Kleber, Florian In der Gemeinsamen Normdatei der DNB nachschlagen ; Diem, Markus In der Gemeinsamen Normdatei der DNB nachschlagen ; Christlein, Vincent In der Gemeinsamen Normdatei der DNB nachschlagen ; Louloudis, Georgios ; Stamatopoulos, Nikolaos ; Gatos, Basilis
Erschienen in
2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan, 2017, S. 1377-1382
Erschienen2017
Ausgabe
Accepted version
SpracheEnglisch
DokumenttypAufsatz in einem Sammelwerk
Schlagwörter (DE)Schreiberidentifizierung
Schlagwörter (EN)Writer Identification / Competition / Dataset / Compter vision
Projekt-/ReportnummerEuropean Union's Horizon 2020: 674943
ISBN978-1-5386-3586-5
ISSN2379-2140
URNurn:nbn:at:at-ubtuw:3-3375 Persistent Identifier (URN)
DOI10.1109/ICDAR.2017.225 
Zugriffsbeschränkung
 Das Werk ist frei verfügbar
Dateien
ICDAR2017 Competition on Historical Document Writer Identification (Historical-WI) [3.45 mb]
Links
Nachweis
Klassifikation
Zusammenfassung (Englisch)

The ICDAR 2017 Competition on Historical Document Writer Identification is dedicated to record the most recent advances made in the field of writer identification. The goal of the writer identification task is the retrieval of pages, which have been written by the same author. The test dataset used in this competition consists of 3600 handwritten pages originating from 13th to 20th century. It contains manuscripts from 720 different writers where each writer contributed five pages. This paper describes the dataset, as well as the details of the competition. Five different institutions submitted six methods which were ranked using identification and retrieval metrics. The paper describes the competition details including the dataset, the evaluation measures used as well as a short description of each submitted method.

Notiz
Statistik
Das PDF-Dokument wurde 18 mal heruntergeladen.