Using stochastic grammars for modelling and recognising cursive script
Using stochastic grammars for modelling and recognising cursive script
Presents a new approach to cursive script recognition which combines syntactic pattern recognition with neural networks. This has a number of advantages over previous methods. First, the ability to infer complex internal representations which are abstracted from time allows the input data to be modelled efficiently. Second, the fact that no segmentation is required should lead to robust performance, though we have not yet tested this on a large cursive script database. Third, due to the highly structured way in which the data is modelled it is quite feasible to recognise a small vocabulary with a non-stochastic temporal connectionist parser TCP. This requires only AND gates, OR gates and shift registers, and is therefore easy to implement in silicon. Finally, the TCP's ability to learn in an unsupervised fashion is interesting both in terms of machine-learning theory, and in practical terms, since it reduces the need for manual labelling in large training databases.
3/1-3/4
Lucas, S.M.
c9cb456d-a8b1-4721-be9b-17147331b718
Damper, R.I.
6e0e7fdc-57ec-44d4-bc0f-029d17ba441d
1989
Lucas, S.M.
c9cb456d-a8b1-4721-be9b-17147331b718
Damper, R.I.
6e0e7fdc-57ec-44d4-bc0f-029d17ba441d
Lucas, S.M. and Damper, R.I.
(1989)
Using stochastic grammars for modelling and recognising cursive script.
IEE Colloquium on Character Recognition and Applications.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
Presents a new approach to cursive script recognition which combines syntactic pattern recognition with neural networks. This has a number of advantages over previous methods. First, the ability to infer complex internal representations which are abstracted from time allows the input data to be modelled efficiently. Second, the fact that no segmentation is required should lead to robust performance, though we have not yet tested this on a large cursive script database. Third, due to the highly structured way in which the data is modelled it is quite feasible to recognise a small vocabulary with a non-stochastic temporal connectionist parser TCP. This requires only AND gates, OR gates and shift registers, and is therefore easy to implement in silicon. Finally, the TCP's ability to learn in an unsupervised fashion is interesting both in terms of machine-learning theory, and in practical terms, since it reduces the need for manual labelling in large training databases.
This record has no associated files available for download.
More information
Published date: 1989
Additional Information:
Address: London, UK
Venue - Dates:
IEE Colloquium on Character Recognition and Applications, 1989-01-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 256257
URI: http://eprints.soton.ac.uk/id/eprint/256257
PURE UUID: e25617c4-dabb-4a4c-bf55-b2cb91f9c9a8
Catalogue record
Date deposited: 07 Jan 2002
Last modified: 10 Dec 2021 20:42
Export record
Contributors
Author:
S.M. Lucas
Author:
R.I. Damper
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics