Computational Analysis of Handwriting Style

9
Nicht eingeplant
20m
Von-Melle-Park 4

Von-Melle-Park 4

Poster

Beschreibung

Images of digitised historical written artefacts contain much more information than the mere textual content found in their transcriptions, such as the texture of writing support, the general visual layout, and the non-textual visual elements. Among these aspects, the style of handwriting itself can tell us about the scribe, the approximate place of origin, and perhaps even help date the artefact itself. Therefore, handwriting style analysis is one of the very important topics in our research. To meet the different requirements of our research questions, we developed a novel training-free classifier, as well as a similarity measurement approach for the tasks of classifying the handwriting style, scribe identification, and measuring the similarity between handwritten samples.

Keywords

Visual-Pattern Classification
Handwriting Style Analysis
Writer Identification
Historical Document Analysis

Autor

Dr. Hussein Mohammed (Universität Hamburg / The Cluster of Excellence: UWA)

Präsentationsmaterialien

Es gibt derzeit keine Materialien.