Handling Diacritical Marks for Online Arabic Script Based Languages Character Recognition using Fuzzy c-mean Clustering and Relative Position

Arabic script is used by more than 1/4th population of the world in the form of different languages like Arabic, Persian, Urdu, Sindhi, Pashto etc whereas each language has its own words meaning, grammatical and writing rules and set of alphabets. Whereas on the other hand it is very difficult to deal with Arabic script based languages due its complex nature of this script. Moreover these language are rich in diacritical marks associated with each character and it is one of the main issue due to variability, position, shape and association with different character. We present a novel technique to handle diacritical marks based on the relative position of diacritical marks with respect to associated character and using mean of fuzzy c-mean which determined each cluster location using member defuzzification and stroke order. The diacritical marks concerned character is estimated by combining the position information and fuzzy mapping on to the character. Experiment shows that the proposed technique preformed well to deal with diacritical marks.