Analysis of the South Slavic Scripts by Run-Length Features of the Image Texture

TL;DR

This paper introduces a script recognition algorithm based on run-length texture features derived from coded image textures of South Slavic scripts, achieving effective differentiation among Cyrillic, Latin, and Glagolitic scripts.

Contribution

The study presents a novel texture-based script recognition method using run-length features applied to coded image textures of South Slavic scripts.

Findings

3 out of 5 run-length features effectively differentiate scripts

The algorithm performs well on a custom database of Cyrillic, Latin, and Glagolitic texts

Texture analysis can be a viable approach for script recognition in South Slavic languages.

Abstract

The paper proposes an algorithm for the script recognition based on the texture characteristics. The image texture is achieved by coding each letter with the equivalent script type (number code) according to its position in the text line. Each code is transformed into equivalent gray level pixel creating an 1-D image. Then, the image texture is subjected to the run-length analysis. This analysis extracts the run-length features, which are classified to make a distinction between the scripts under consideration. In the experiment, a custom oriented database is subject to the proposed algorithm. The database consists of some text documents written in Cyrillic, Latin and Glagolitic scripts. Furthermore, it is divided into training and test parts. The results of the experiment show that 3 out of 5 run-length features can be used for effective differentiation between the analyzed South Slavic scripts.