FUZZY BASED PREPROCESSING USING FUSION OF ONLINE AND OFFLINE TRAIT FOR ONLINE URDU SCRIPT BASEDLANGUAGES CHARACTER RECOGNITION

Character recognition has been fascinating and intense field of pattern recognitionresearch since early days of computer. This task becomes more challenging whenit involves Urdu script based languages especially written in handwritten Nasta’liq fontdue to the large variations and complexity of the script. Fuzzy logic is an important toolto deal with vague, incomplete, noisy and contradictory information. In order to makehandwritten communication with machine more natural, we propose several preprocessingsteps for handwritten online Urdu script character recognition to overcome the issue inraw input. We present fuzzy based several preprocessing operations in order to normalizethe handwritten stroke using both online and offline domain. The proposed technique isalso the necessary step towards character recognition, person identification, personalitydetermination where input data are processed from all perspectives.