Baseline-based zoning design for the NSHPZ-HMM 2-D model applied to Arabic script

In this paper, we present the first truly 2-D recognition system of Arabic handwritten words. The used recognizer is the NSHP
^Z
-HMM model with a new zoning design approach. The zoning method we propose depends on the baseline of the treated word. The key point relies in the ability of our baseline to perfectly follow the writing curve even in case of vertical ligatures and of different slant angles within the same Arabic word. The result is an appropriate division in zones of an image word that facilitates its modelization through the use of the NSHP
^Z
-HMM model. Experiments on Arabic literal amounts of AHDB database show the efficiency of the proposed recognition system over an NSHP
^Z
-HMM using zoning independent baseline, a classical pixel-based NSHP-HMM and a set of state of the art systems developed on the same database.