An Approach to the Analysis of the South Slavic Medieval Labels Using Image Texture

TL;DR

This paper introduces a novel texture-based script classification method for South Slavic medieval labels, effectively distinguishing different script types through statistical and pattern analysis of coded text features.

Contribution

It presents a new approach combining run-length and local binary pattern analysis for script classification, extending existing document clustering techniques.

Findings

Effective differentiation of script types achieved

High accuracy demonstrated on historical labels

Method proves robust for various script styles

Abstract

The paper presents a new script classification method for the discrimination of the South Slavic medieval labels. It consists in the textural analysis of the script types. In the first step, each letter is coded by the equivalent script type, which is defined by its typographical features. Obtained coded text is subjected to the run-length statistical analysis and to the adjacent local binary pattern analysis in order to extract the features. The result shows a diversity between the extracted features of the scripts, which makes the feature classification more effective. It is the basis for the classification process of the script identification by using an extension of a state-of-the-art approach for document clustering. The proposed method is evaluated on an example of hand-engraved in stone and hand-printed in paper labels in old Cyrillic, angular and round Glagolitic. Experiments demonstrate very positive results, which prove the effectiveness of the proposed method.