View article

The style of writing or calligraphy applied in ancient manuscripts gives useful information to paleographers. The information helps paleographer to identify date, writer, number of writers, place of origin, and the originality of manuscripts. This information is known as features. The features from characters, tangent value, dominant background and also Grey-Level Co-occurrence Matrix (GLCM) have been used in this field of research. A novel technique was proposed for digital Jawi Paleography. Jawi is the original Malay writing based on Arabic characters. The technique proposed models triangles on images and extracts features from them. The features are used for classification. In this paper, new features for the Triangle Model are proposed. Also, the implementation of four zones is reported. The number of features has been extended from 12 to 45. For validation of proposed algorithm, 60,000: 20,000 training and testing data from Hoda digit dataset has been prepared, selected randomly for 10 rounds of testing. For further verification, two Supervised Machine Learning (SML) and three Unsupervised Machine Learning (UML) algorithms were experimented. These experiments were conducted using a new Arabic calligraphy dataset that was set up from 1,225 Arabic letters taken from calligraphy books. From the data, SML experiments were conducted with the ratio of 807: 408 for training and testing. Whereas for the UML, three classifiers were tested on 30 images of Arabic calligraphy dataset. Results from the tests prove that the Triangle Model technique can successfully be used in digital paleography of Jawi characters.