Segmentation of Cehari + Consonant combination strokes in online Handwritten Gurmukhi Script Recognition

Abstract

Online handwriting recognition has been worked upon for a long time now. It has been done for various scripts all over the world. Great milestones have been reached in research for the online handwriting recognition for Indian scripts as well. We decided to work on Gurmukhi script. The fastness in writing Gurumukhi has led to the cursive nature of the script, there by leading to a combination of strokes written in a single stroke. These types of strokes are unrecognizable to the classifier. Segmentation algorithms are proposed that use the slope calculation method at every point and find candidate points for segmenting the stroke into individual basic strokes. The candidate points is a segmenting points, more than one candidate points may be present in the text. The algorithms demonstrated an accuracy of 96.5% in segmenting various stroke combinations when written in a single stroke.