A Three Stages Segmentation Model for a Higher Accurate off-line Arabic Handwriting Recognition

Arabic handwriting recognition considers a one of the hardest applications of OCR system. The reason of that relates to characteristics of Arabic characters and the way of writing cursively. Furthermore, no rules can control on handwriting way, different styles, sizes and curves make the process of recognition is very complex. On other side, the key for reaching to good recognition is by getting a correct segmentation. Actually, the way of segmentation is important, because if there is a small part is not clear in character that will reflect on recognition process. In this paper we aim to enhance the accuracy of off-line Arabic Hand Written text segmentation. Three stages are proposed to reach to highest ratio of segmentation. Line segmentation is the first stage, where it is proposed to separate each line. We depend on row density to predict spaces among lines. Second stage is Object segmentation and it is proposed to segment each word or sub word. Eight neighbors connectivity are used to detect connected pixels. Final stage is shape segmentation which is proposed to segment sub word to characters. The idea in this stage is finding segmentation points among branch points in the baseline. To apply that we propose four threshold values to investigate on each branch point. The result was satisfactory and the model proved a good ability to tackle different types of texts with bad samples.