Recognition for old Arabic manuscripts using spatial gray level dependence (SGLD)

Texture analysis forms the basis of object recognition and classification in several domains, one of these domains is historical document manuscripts because the manuscripts hold our culture heritage and also large numbers of undated manuscripts exist. This paper presents results for historical document classification of old Arabic manuscripts using texture analysis and a segmentation free approach. The main objective is to discriminate between historical documents of different writing styles to three different ages: Contemporary (Modern) Age, Ottoman Age and Mamluk Age. This classification depends on a Spatial Gray-level Dependence (SGLD) technique which provides eight distinct texture features for each sample document. We applied Stepwise Discriminant Analysis and Multiple discriminant analysis methods to decrease the dimensionality of features and extract training vector features from samples. To classify historical documents into three main historical age classes the decision tree classification is applied. The system has been tested on 48 Arabic historical manuscripts documents from the Dar Al-Kotob Al-Masria Library. Our results so far yield 95.83% correct classification for the historical Arabic documents.