This paper describes a new feature set, called the extended directionalfeatures (EDF) for use in the recognition of online handwritten strokes. We useEDF specifically to recognize strokes that form a basis for producingDevanagari script, which is the most widely used Indian language script. Itshould be noted that stroke recognition in handwritten script is equivalent tophoneme recognition in speech signals and is generally very poor and of theorder of 20% for singing voice. Experiments are conducted for the automaticrecognition of isolated handwritten strokes. Initially we describe the proposedfeature set, namely EDF and then show how this feature can be effectivelyutilized for writer independent script recognition through stroke recognition.Experimental results show that the extended directional feature set performswell with about 65+% stroke level recognition accuracy for writer independentdata set.
展开▼
