Online recognition of multi-stroke handwritten Urdu characters

Character recognition has enjoyed a lot of research in the recent past. Good recognition systems are available commercially for alphabetical languages based on Roman characters and for symbolic languages like Chinese. But languages based on Arabic alphabets like Arabic, Urdu etc. do not have such recognition systems. The recognition systems generally have a scanner or camera as the input device for off-line recognition, or a stylus/tablet as input device for online recognition. These systems are used in conjunction with the input peripheral devices like keyboards and mice. With the recent developments in electronic tablets, pen movements can be captured more accurately. This paper presents part of the work for online recognition of handwritten Urdu language characters. Urdu language is based on Arabic alphabets with larger character set as compared to Arabic (37 characters). Urdu, due to its large character set and limited number strokes, is difficult to recognize. Many characters are similar with little differences. Online recognition of multi stroke (two-, three-, and four-stroke) handwritten Urdu characters is presented in this paper, whereas, single-stroke character recognition was presented in a preceding work. After necessary preprocessing, some novel features are extracted. Various types of classification methodologies are then tested in order to find the best combination of features and classifiers for two-, three-, and four-strokes handwritten Urdu characters recognition.