| Popis: |
Many researches and historians from all around the world are interested in historical Ottoman archives. However, translation of these documents requires competent historians which is not a feasible method in terms of time and cost. Thus, automatic translation of these documents are required. In this paper, preprocessing steps of accessing the Ottoman manuscripts with a word based search engine is studied. These preprocessing steps are binarization and line segmentation of digitalized documents. The traditional line segmentation methods applied to printed documents do not yield to satisfactory results for historical and handwritten documents. Due to this fact, more complex line segmentation techniques must be used. In this study, we developed a projection profile based method for line segmentation and local binarization is used. The experiments are conducted on a 120 page Ottoman archive and the results show that the proposed system is successful. |
