Abstract
This paper proposes a novel and an effective ap-proach to classify ancient Arabic manuscripts in “Naskh” and “Reqaa” styles. This work applies SIFT and SURF algorithms to extract the features and then uses several machine learning algorithms: Gaussian Na¨ıve Bayes (GNB), Decision Tree (DT), Random Forest (RF) and K-Nearest Neighbor (KNN) classifiers. The contribution of this work is the introduction of synthetic features that enhance the classification performance. The training phase encompasses four training models for each style. For testing purposes, two famous books from the Islamic literature are used: 1) Al-kouakeb Al-dorya fi Sharh Saheeh Al-Bokhary; and 2) Alfaiet Ebn Malek: Mosl Al-tolab Le Quaed Al-earab. The experimental results show that the proposed algorithm yields a higher accuracy with SIFT than with SURF which could be attributed to the nature of the dataset.
Highlights
Ancient manuscripts (AMs) are considered references for several centuries in history and witness on human literature and development
We propose a model for classifying Arabic writing styles in ancient Arabic manuscripts using novel models for training
The features have been extracted by using scale-invariant feature transform (SIFT) and SURF algorithms
Summary
Ancient manuscripts (AMs) are considered references for several centuries in history and witness on human literature and development. Since Arabic manuscripts have several styles of writing which differ according to area, country, occasion and materials. We take into consideration the horizontal projection profiles of Arabic texts that have a single peak around the middle of the text-line and the alphabet letters whose shapes differ according to the location of a letter – beginning, middle or at the end of the word. Another level of difficulty is that Arabic manuscripts vary over the ages, from writer to another and this introduces variability (in the learnt features).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have