Effective Technique for the Recognition of Writer Independent Off-Line Handwritten Arabic Words

In this paper we present a novel segmentation-free Arabic handwriting recognition system based on hidden Markov model (HMM). Two main contributions are introduced: a novel pre-processing method and a new technique for dividing the image into non uniform horizontal segments to extract the features. The proposed system first pre-processes the input image by setting the thickness of the input word to three pixels and fixing the spacing between the different parts of the word. The input image is then divided into constant number of non uniform horizontal segments depending on the distribution of the foreground pixels. A set of robust features representing the foreground pixels is extracted using vertical sliding windows. The proposed system builds character HMM models and learns word HMM models using embedded training data. The performance of the proposed system is very promising compared with other Arabic handwriting recognition systems available in the literature.