A New Method for Line Segmentation of Persian Handwritten Documents

In this paper, a new method for finding of the lines segmentation in Persian handwritten texts, is presented. At first, we remove the slants and dots that, which are located between the lines, then cut the connected components height. The next step we connect the words in each line, after connecting words we consider the lowest black pixel in each line as a separate line. The performances of proposed method have been evaluated in standard data base that includes all the challenges in lines segmentation. The results show that this method has good potential

کلیدواژه ها:

Textual line segmentation ، Persian handwritten recognition