Offline handwritten Arabic cursive text recognition using Hidden Markov Models and re-ranking

Jawad H AlKhateeb, Jinchang Ren, Jianmin Jiang, Husni Al-Muhtaseb
2011 Pattern Recognition Letters  
2011) Offline handwritten Arabic cursive text recognition using hidden markov models and re-ranking. Pattern Recognition Letters, 32 (8). Abstract: Recognition of handwritten Arabic cursive texts is a complex task due to the 19 similarities between letters under different writing styles. In this paper, a word-based off-line 20 recognition system is proposed, using Hidden Markov Models (HMMs). The method 21 employed involves three stages, namely preprocessing, feature extraction and 22
more » ... tion. First, words from input scripts are segmented and normalized. Then, a 23 set of intensity features are extracted from each of the segmented words, which is 24 based on a sliding window moving across each mirrored word image. Meanwhile, 25 structure-like features are also extracted including number of subwords and diacritical 26 marks. Finally, these features are applied in a combined scheme for classification. 27 Intensity features are used to train a HMM classifier, whose results are re-ranked 28 using structure-like features for improved recognition rate. In order to validate the 29 proposed techniques, extensive experiments were carried out using the IFN/ENIT 30 database which contains 32492 handwritten Arabic words. The proposed algorithm 31 yields superior results of improved accuracy in comparison with several typical 32 methods. 33 34
doi:10.1016/j.patrec.2011.02.006 fatcat:dvsxzyip75e6pisf3vpy6mrg2u