Arabic OCR: A centerline independent segmentation technique

The cursive written text is still representing a challenge for researchers. Latin and Chinese Optical Character Recognition systems (OCR) have been studied extensively in the literature. Yet little work was performed for Arabic character recognition. Powerful and stable text segmentation is still needed. In this paper, a segmentation technique which is capable of processing vowelized Arabic text is introduced. Such a technique is size and font independent. Moreover, it does not require the detection of the centerline. It can also process typeset text. This technique can segment the cursive written text line even if the line suffers from skewness.