Document Image Coding and Clustering for Script Discrimination

TL;DR

This paper presents a novel script discrimination method for documents by converting text into coded images and applying texture analysis and clustering, effectively distinguishing various historical scripts.

Contribution

It introduces a new coding and texture analysis approach combined with clustering for script discrimination, outperforming existing methods on historical document datasets.

Findings

Superior accuracy on historical script datasets

Effective differentiation of Cyrillic, Glagolitic, Antiqua, and Fraktur scripts

Outperforms state-of-the-art methods in script classification

Abstract

The paper introduces a new method for discrimination of documents given in different scripts. The document is mapped into a uniformly coded text of numerical values. It is derived from the position of the letters in the text line, based on their typographical characteristics. Each code is considered as a gray level. Accordingly, the coded text determines a 1-D image, on which texture analysis by run-length statistics and local binary pattern is performed. It defines feature vectors representing the script content of the document. A modified clustering approach employed on document feature vector groups documents written in the same script. Experimentation performed on two custom oriented databases of historical documents in old Cyrillic, angular and round Glagolitic as well as Antiqua and Fraktur scripts demonstrates the superiority of the proposed method with respect to well-known methods in the state-of-the-art.