Abstract
In this paper, we present a segmentation method of handwritten Arabic texts. The proposed method uses the algorithm for construction of the Outer Isothetic Cover (OIC) of a digital object. This technique 3allows the construction of polygons of all connected components on the binary image of the document. The first specificity of this method is that it allows the extraction of the shape of the script. Its second specificity is its independency from the variability of script size in the same document. The main objective of this work is to develop a nontime nor memory consuming segmentation method in order to be integrated to a mobile system for tutorial and guiding of pilgrimage (HAJJ) steps based on geo-localization (GPS). Obtained text will be analyzed by an intelligent system to extract HAJJ rules that will be integrated with the time and the position of the person doing the pilgrimage (HAJEEJ) to inform him about the following required step of his HAJJ. The proposed method has been evaluated on different databases and compared to another one from the literature [2]. In this paper we used big data of specific documents of HAJJ and Umra rules to evaluate time and memory consuming which is necessary for mobile applications.