Automatic Handwriting Identification on Medieval Documents

In this paper, we evaluate the performance of textindependent writer identification methods on a handwriting dataset containing medieval English documents. Applicable identification rates are achieved by combining textural features (joint directional probability distributions) with allographic features (grapheme-emission distributions). The aim is to develop an automatic handwriting identification tool that can assist the paleographer in the task of determining the authorship of historical manuscripts.

• Type: Conference
• Year: 2007
• Where: ICIAP
• Authors: Marius Bulacu, Lambert Schomaker
• Keywords: Applicable Identification Rates, Automatic Handwriting Identification, Directional Probability Distributions, ICIAP 2007, Image Processing