A Novel Secant Based Method for Recognition of Handwritten Pitman Shorthand Language Consonants and Vowels

Abstract

Pitman Shorthand Language (PSL) is a phonetic based language developed in 1837 to translate speech into text. Recognition of text recorded in PSL is an interesting research problem. The PSL has the practical advantage of high speed of recording, more than 120-200 words per minute, because of which it is universally acknowledged. This recording medium has its continued existence inspite of considerable developments in speech processing systems, which are not universally established yet. In order to exploit the vast transcribing potential of PSL a new area of research on automation of PSL processing is conceived.In this work, we have proposed the secant based method for recognition of PSL characters. The work comprises of preprocessing such as thinning and filling, determination of end points of the handwritten strokes. Slope of the strokes are determined using end points of the stroke. Characters are classified based on the estimated slopes of secants and other features such as stroke type and thickness. The vowels are classified based on the vowel type such as dash or dot and thickness and position with respect to a stroke. The proposed work is thoroughly tested for a large number of handwritten strokes. The recognition rates are estimated and found to be in the range of 60 to 95 %.

A Neural Network based Method for Recognition of Handwritten English Pitman's Shorthand

“…The present work is concerned to substitution of equivalent English words, for the phonetic compositions of the transcribed words in the process of automatic generation of English text from existing PSL document. The present work is the development of a method for recognition of handwritten PSL words [1], thus facilitating automation of English text generation from written PSL written documents. In this research area, there are two approaches available.…”