Use this URL to cite or link to this record in EThOS:
Title: Lexicon Organisation and Contextual Methods for Online Handwritten Pitman's Shorthand Recognition
Author: Htwe, Swe Myo
ISNI:       0000 0001 3583 0571
Awarding Body: University of Nottingham
Current Institution: University of Nottingham
Date of Award: 2007
Availability of Full Text:
Access from EThOS:
This research investigates novel solutions to the computer transcription Of handwritten Pitman's Shorthand as a rapid means of text entry (up to 100 words per minute) into today's pen-based handheld devices. Two mathematical models are developed in this work. The first deals with high level phoneticbased translation, while the second specifically concerns low level primitive-based translation. Both models are closely related to the lexicon organisation and contextual processing for online handwritten Pitman's Shorthand recognition. A number of research issues that arise from interpreting handwritten Pitman's Shorthand strokes ofdigital ink as text are addressed including: (a) a feasibility study into improving a conventional phonetic-based transliteration approach to advance word recognition; (b) an investigation into new Bayesian Network modelling of strokes and their relationships in order to solve the problem ofgeometric variations and vowel ambiguities of handwritten Pitman's Shorthand; (c) generation of a new machine-readable Pitman's Shorthand lexicon to facilitate the direct transcription of geometric features of Pitman's Shorthand into English text; (d) analysis of the impact of statistical language modelling in handwriting phrase recognition; (e) and a discussion of the graphical user interface issues in relation to the development of a commercial prototype from the frame ofreference ofthis research. The research has been carried out in close cooperation with Nanyang Technology University (NTU) in Singapore. The system is currently under a final evaluation in terms of its recognition accuracy, as well as its potential to be introduced as a commercially viable fast text input system.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available