Fractal algorithms and RGB image processing in scribal and ink identification on an 1819 secret initiation manuscript to the “Philike Hetaereia”

Abstract

Historical texts incorporate important characteristics that need to be assessed including genre, text structure and content. Often overlooked are characteristics of handwritten manuscripts commonly divided into legibility, readability and aesthetics. To determine the scientific feasibility of classification of handwritten texts an objective approach is developed to describe twenty handwritten pages of an 1819 Greek manuscript, that refers to the initiation to the Greek secret “friendly society” (Philike Hetaereia) organization, established as part of the Greek independence against the Ottoman Turks. It is investigated through a fractal and RGB image analysis approach. Fractal Minkowski Dimension was applied on the handwritten text and the RGB color analysis on the ink and paper and both were used as a non-invasive manner and revealed interesting results. The novel RGB image analysis and the fractal analysis of the manuscript identified respectively, five iron gall inks and four scribes from the ink content and handwritten styles, of the compact five lines text and whole text pages. The novel approach was verified with another old manuscript of known ink pigments, as well as with thirteen known handwritten texts of that period and four prints representing modern and similar period texts substantiating the findings of the novel methods.

Handwriting-Based Text Line Segmentation from Malayalam Documents

“…Some of these possible cases are illustrated in Figure 1. All these factors make the recognition of handwritten documents in this language a complex problem [1,2]. Therefore, the development of OCR for the recognition of unconstrained handwritten document images for the Malayalam language has not progressed yet.…”