Skip to main navigation Skip to search Skip to main content

Post Processing of Handwritten Phonetic Pitman's Shorthand Using a Bayesian Network Built on Geometric Attributes

  • Swe Myo Htwe
  • , Colin Higgins
  • , Graham Leedham
  • , Ma Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we introduce a new approach to the computer transcription of handwritten Pitman shorthand as a rapid means of text entry (up to 100 words per minute) into today's handheld devices, almost at the rate of speech. It is different from previous applications of the same framework from two aspects: - firstly, a novel idea of using geometric attributes other than phonetic attributes in the abstraction of a phonetic Pitman's shorthand lexicon is proposed. Secondly, a Bayesian network representation for the organisation of shorthand-outline models is introduced, in which natural variability of Pitman shorthand is defined via different nodes and links. Using a probabilistic Bayesian network, the system shows a noticeable robustness not only in transcribing a variety of genuine handwriting, but also in estimating missing vowel components that may have been omitted in speed writing. The accuracy of the new approach (92.86%) is a considerable improvement over previous applications.
Original languageEnglish
Title of host publicationPattern Recognition and Data Mining: Third International Conference on Advances in Pattern Recognition, ICAR 2005, Bath, UK, August 22-25, 2005, Part I
EditorsSameer Singh, Maneesha Singh, Chid Apte, Petra Perner
Place of PublicationBerlin, Germany
PublisherSpringer
Pages569-579
Volume1
ISBN (Print)3540287574, 9783540287575
DOIs
Publication statusPublished - 2005
EventICAPR 2005: 3rd International Conference on Advances in Pattern Recognition - Bath, United Kingdom
Duration: 22 Aug 200525 Aug 2005

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Number3686
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceICAPR 2005: 3rd International Conference on Advances in Pattern Recognition
CityBath, United Kingdom
Period22/08/0525/08/05

Keywords

  • Artificial Intelligence and Image Processing
  • Pattern Recognition and Data Mining
  • Image Processing

Fingerprint

Dive into the research topics of 'Post Processing of Handwritten Phonetic Pitman's Shorthand Using a Bayesian Network Built on Geometric Attributes'. Together they form a unique fingerprint.

Cite this