Universal Graphical User Interface for Online Handwritten Character Recognition

Abstract

Handwritten character segmentation is the process of dividing a character into multiple segments so that it can be passed to the recognition system and on the basis of these segments the recognition system can recognize that particular character. In this process user provides the input through any touch devices like PDA, Mobiles or by the Tablets and the segmentation tool takes the input and break the character into segments. There are various tools available which performs the segmentation but no one is available in all the platforms. The aim of this thesis is to represent a methodology which does not segment the characters on the basis of their shapes. Instead of segmenting the character on the basis of their shapes, it divides the character into the points. It finds the co-ordinate of the every point where pen move from the pen down to pen up. This is a platform independent tool that runs online on any browser which is HTML5 enabled. Since it does not depend upon the shape of the character, it segments more efficiently than other tools.