A Preprocessing Model for Hand-Written Arabic Texts Based on Voronoi Diagrams

In this paper, a preprocessing model for hand-written Arabic text on the basis of the Voronoi Diagrams (VDs) is presented and discussed. The proposed VD-based pre-processing model consists of five stages: a preparatory stage, page segmentation, thinning, baseline estimation, and slanting correction. In the preparatory stage, the text image is converted via VDs into a group of geometrical forms that consist of edges and vertices that are used to create the other stages of the proposed model. This stage consists of four main processes: binarization, edge extraction and contour tracking, sampling, and point-VD construction. The second stage is the page segmentation stage based on the VD area. In the third stage, an efficient method for text structuring (that is, thinning) is presented. In the fourth stage, a novel baseline based VD method is presented. In the fifth stage, an efficient technique for slanting detection and correction is proposed and discussed.