Segmentation and Recognition of Vocalized Outlines in Pitman Shorthand

Abstract

There is a wish to be able to enter text into mobile computing devices at the speed of speech. Only handwritten shorthand schemes can achieve this data recording rate. A novel approach to the recognition of vocalized outlines in Pitman's shorthand is proposed in this paper. In this approach, the recognition process is divided into two steps. The consonant outline is first recognized by a two-stage (segmentation and classification) approach. Afterwards surrounding vowel and diphthong symbols are classified and their positions in relation to an associated consonant stroke are determined. Promising results of over 70% recognition accuracy have been obtained.