A new method to separation of Farsi and Arabic sub-words using image processing techniques

Letters separation and word´s units is one of the most important parts of text recognition algorithms. In the Farsi language, these parts consist of single letters and connected letters which called “sub-word”. Therefore, separation for these units has a main role in developing text processing´s algorithms. In this paper, a method based on connected-component labeling techniques with high accuracy is suggested that makes letters and sub-words separation in Farsi font in any size, possible. Experiments show more than 90 percent accuracy in this method.