Writer identification using text line based features

Abstract

We present a system for writer identification. From handwritten lines of text, twelve features are extracted which are used to recognize persons, based on their handwriting. The features extracted mainly correspond to visible characteristics of the writing, for example, the width, the slant and the height of the three main writing zones. Additionally, features based on the fractal behavior of the writing, which are correlated with the writing's legibility, are used. With these features two classifiers are applied: a k-nearest neighbor and a feedforward neural network classifier. In the experiments, 100 pages of text written by 20 different writers are used. By classifying individual text lines, an average recognition rate of 87.8% for the k-nearest neighbor and 90.7% for the neural network is measured. By a simple maximum ranking over all lines of a page, all texts are correctly assigned to the corresponding writers. Compared to these results, an average recognition rate of 98% was measured when humans assigned persons to the text lines.